SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.01648 · 2023

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation

arXiv · PDF · Open in the Atlas

Code that ran

7 of 13 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 6 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/2312.01648.json · badge: /api/ran/2312.01648.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
randallbalestriero/splinellm canonical (classifier label)
classifier basis: census
7 ran · 6 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
randallbalestriero/splinellm/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, randallbalestriero/splinellm 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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
randallbalestriero/splinellm/modeling_llama.py
pointer only (licence: NONE) · get_code("f725bc2d76076485")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, randallbalestriero/splinellm 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.

fit_sup Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
randallbalestriero/splinellm/statistic_analysis.py
pointer only (licence: NOASSERTION) · get_code("12a12995c1053234")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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_data Ran
ran; our contract draft was wrong, not the code
randallbalestriero/splinellm/statistic_analysis.py
pointer only (licence: NOASSERTION) · get_code("23e3672bc122afcc")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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_data Ran
ran; our contract draft was wrong, not the code
randallbalestriero/splinellm/text_features_figure.py
pointer only (licence: NOASSERTION) · get_code("14bcb35bbf9ee4d1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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
randallbalestriero/splinellm/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, randallbalestriero/splinellm 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.

text_with_autofit Ran
ran; our contract draft was wrong, not the code
randallbalestriero/splinellm/text_features_figure.py
pointer only (licence: NOASSERTION) · get_code("949a366d9461e73b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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.

classify_dataset Not yet run
unverified (harvested, no recorded run)
randallbalestriero/splinellm/huggingface_classifiers.py
pointer only (licence: NOASSERTION) · get_code("c2f133d308ead1c4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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.

clustering Not yet run
unverified (harvested, no recorded run)
randallbalestriero/splinellm/statistic_analysis.py
pointer only (licence: NOASSERTION) · get_code("5c0bfe90ef68eed9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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.

generative_model_inference Not yet run
unverified (harvested, no recorded run)
randallbalestriero/splinellm/generation_utils.py
pointer only (licence: NOASSERTION) · get_code("f5cfb4bc1437b436")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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.

get_dataset Not yet run
unverified (harvested, no recorded run)
randallbalestriero/splinellm/data_utils.py
pointer only (licence: NOASSERTION) · get_code("edb3dc8a5aa98bf3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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.

load_generative_model_and_tokenizer Not yet run
unverified (harvested, no recorded run)
randallbalestriero/splinellm/generation_utils.py
pointer only (licence: NOASSERTION) · get_code("21e2a016b769f048")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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.

load_pile Not yet run
unverified (harvested, no recorded run)
randallbalestriero/splinellm/data_utils.py
pointer only (licence: NOASSERTION) · get_code("2315da591a30fd63")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, randallbalestriero/splinellm (NOASSERTION). 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 later) and 10 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
47 dated earlier, 10 the same month, 300 later, 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
19 dated earlier, 4 the same month, 218 later, 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 83 other papers
13 dated earlier, 1 the same month, 69 later · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here

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) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In particular, we develop in closed form $(i)$ the intrinsic dimension in which the Multi-Head Attention embeddings are constrained to exist and $(ii)$ the partition and per-region affine mappings of the feedforward (MLP) network of LLMs' layers. Our theoretical findings further enable the design of novel principled solutions applicable to state-of-the-art LLMs. First, we show that, through our geometric understanding, we can bypass LLMs' RLHF protection by controlling the embedding's intrinsic dimension through informed prompt manipulation. Second, we derive interpretable geometrical features that can be extracted from any (pre-trained) LLM, providing a rich abstract representation of their inputs. We observe that these features are sufficient to help solve toxicity detection, and even allow the identification of various types of toxicity. Our results demonstrate how, even in large-scale regimes, exact theoretical results can answer practical questions in LLMs. Code: https://github.com/RandallBalestriero/SplineLLM

For agents

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

get_harvested_code_for_paper("2312.01648")
get_code_for_paper("2312.01648")
have("2312.01648")

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

curl https://syntology.ai/api/ran/2312.01648.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.01648.svg)](https://syntology.ai/paper/2312.01648)

Connect an agent — have() is free.