SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.12299 · 2024

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 10 failures of our instrument; 1 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.12299.json · badge: /api/ran/2410.12299.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
weixuan-wang123/SADI canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
weixuan-wang123/SADI/modeling_llama.py
pointer only (licence: NONE) · get_code("30d7eec482ebf6b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_rotary_pos_emb Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/modeling_llama.py
pointer only (licence: NONE) · get_code("bac65c3dafaec040")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dict_to_ Ran
ran on a synthesized input
weixuan-wang123/SADI/tok_dataset.py
pointer only (licence: NONE); the stored copy get_code serves, from keltin13/concept-rot, is pointer only (licence: NOASSERTION) · get_code("4b87278bcf65e54d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evalone Ran
ran, honoured the contract we drafted
weixuan-wang123/SADI/steering.py
pointer only (licence: NONE) · get_code("890f9a7e8b35a0ba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

hierarchical_subsequence Ran
ran on a synthesized input
weixuan-wang123/SADI/util/nethook.py
pointer only (licence: NONE) · get_code("920b394e7ad80c53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

length_collation Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/tok_dataset.py
pointer only (licence: NONE); the stored copy get_code serves, from keltin13/concept-rot, is pointer only (licence: NOASSERTION) · get_code("feecc08837987d77")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_mmlu Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/load_dataset.py
pointer only (licence: NONE) · get_code("c0785ff8deb3ee18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_padded_batch Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/tok_dataset.py
pointer only (licence: NONE); the stored copy get_code serves, from keltin13/concept-rot, is pointer only (licence: NOASSERTION) · get_code("59ff38281d7c12b8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

push_key_prefix Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/util/runningstats.py
pointer only (licence: NONE) · get_code("846b749e768edeaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

recursive_copy Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/util/nethook.py
pointer only (licence: NONE); the stored copy get_code serves, from TrustedLLM/UnKE, is pointer only (licence: NONE) · get_code("70f6ab8bde55420e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rotate_half Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/modeling_llama.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sample_portion Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/util/runningstats.py
pointer only (licence: NONE) · get_code("e6620bfaf591afd4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

subsequence Ran
ran; our contract draft was wrong, not the code
weixuan-wang123/SADI/util/nethook.py
pointer only (licence: NONE) · get_code("440ff98c2b1ae1aa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

tally Not yet run
unverified (harvested, no recorded run)
weixuan-wang123/SADI/util/runningstats.py
pointer only (licence: NONE) · get_code("edb0f31cbdd4f7d0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, weixuan-wang123/SADI when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 6 the same month, 9 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
rotate_half 360 other papers
184 dated earlier, 25 the same month, 142 later, 6 same year, order not determinable, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv 243 other papers
119 dated earlier, 24 the same month, 96 later, 2 same year, order not determinable, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
apply_rotary_pos_emb 94 other papers
27 dated earlier, 14 the same month, 49 later, 1 same year, order not determinable, 3 undated · 6 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
2309.11674 (2023-09)
A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
and 91 more not named here
subsequence 49 other papers
30 dated earlier, 3 the same month, 15 later, 1 same year, order not determinable
2007.15646 (2020-07)
Rewriting a Deep Generative Model
2009.05041 (2020-09)
Understanding the Role of Individual Units in a Deep Neural Network
2110.04292 (2021-10)
Toward a Visual Concept Vocabulary for GAN Latent Space
and 46 more not named here
recursive_copy 48 other papers
29 dated earlier, 4 the same month, 14 later, 1 same year, order not determinable
2207.02774 (2022-07)
Local Relighting of Real Scenes
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
and 45 more not named here
hierarchical_subsequence 46 other papers
27 dated earlier, 3 the same month, 15 later, 1 same year, order not determinable
2210.07229 (2022-10)
Mass-Editing Memory in a Transformer
2302.12461 (2023-02)
Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
2311.09053 (2023-11)
Assessing Knowledge Editing in Language Models via Relation Perspective
and 43 more not named here
dict_to_ 3 other papers
2 dated earlier, 1 later
2403.07175 (2024-03)
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
2408.07413 (2024-08)
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
2412.13341 (2024-12)
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
make_padded_batch 3 other papers
2 dated earlier, 1 later
2403.07175 (2024-03)
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
2408.07413 (2024-08)
Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models
2412.13341 (2024-12)
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
length_collation 2 other papers
1 dated earlier, 1 later
2403.07175 (2024-03)
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
2412.13341 (2024-12)
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the behavior of LLMs. Despite considerable interest in this area, current intervention methods exclusively employ a fixed steering vector to modify model activations, lacking adaptability to diverse input semantics. To address this limitation, we propose Semantics-Adaptive Dynamic Intervention (SADI), a novel method that constructs a dynamic steering vector to intervene model activations at inference time. More specifically, SADI utilizes activation differences in contrastive pairs to precisely identify critical elements of an LLM (i.e., attention heads, hidden states, and neurons) for targeted intervention. During inference, SADI dynamically steers model behavior by scaling element-wise activations based on the directions of input semantics. Experimental results show that SADI outperforms established baselines by substantial margins, improving task performance without training. SADI's cost-effectiveness and generalizability across various LLM backbones and tasks highlight its potential as a versatile alignment technique.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.12299")
get_code_for_paper("2410.12299")
have("2410.12299")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.12299.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.12299.svg)](https://syntology.ai/paper/2410.12299)

Connect an agent — have() is free.