SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.03646 · 2024

Locating and Editing Factual Associations in Mamba

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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; 1 no recorded run), 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/2404.03646.json · badge: /api/ran/2404.03646.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
arnab-api/romba canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
MambaBlockForwardPatcher Ran
ran; our contract draft was wrong, not the code
arnab-api/romba/src/hooking/mamba.py
pointer only (licence: NONE) · get_code("eff8297c7f3c1bcd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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.

bytes_to_human_readable Ran
ran; our contract draft was wrong, not the code
arnab-api/romba/src/models.py
pointer only (licence: NONE) · get_code("3d311917c02c1843")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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.

get_color_map Ran
ran; our contract draft was wrong, not the code
arnab-api/romba/src/plotting.py
pointer only (licence: NONE) · get_code("cf3c665c92b7b518")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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.

get_model_size Ran
ran; our contract draft was wrong, not the code
arnab-api/romba/src/models.py
pointer only (licence: NONE) · get_code("9c1a143d0e706278")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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.

get_relation_fn_type Ran
ran; our contract draft was wrong, not the code
arnab-api/romba/src/dataset/dataclasses.py
pointer only (licence: NONE) · get_code("b038315da551dfa2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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_inputs Ran
ran; our contract draft was wrong, not the code
arnab-api/romba/src/functional.py
pointer only (licence: NONE); the stored copy get_code serves, from ledllm/ledllm, is pointer only (licence: NONE) · get_code("96b3625b39d4a804")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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.

replace_eos_with_pad Ran
ran; our contract draft was wrong, not the code
arnab-api/romba/src/tracing.py
pointer only (licence: NONE) · get_code("ee6ae75ce3284a2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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.

selective_scan_with_mask Not yet run
unverified (harvested, no recorded run)
arnab-api/romba/src/hooking/mamba.py
pointer only (licence: NONE) · get_code("5ec1b7c98aef8d41")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, arnab-api/romba 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 7 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
make_inputs 3 other papers
1 dated earlier, 2 later
2312.07876 (2023-12)
Causality Analysis for Evaluating the Security of Large Language Models
2405.18166 (2024-05)
Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
2411.18620 (2024-11)
Cross-modal Information Flow in Multimodal Large Language Models

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

We investigate the mechanisms of factual recall in the Mamba state space model. Our work is inspired by previous findings in autoregressive transformer language models suggesting that their knowledge recall is localized to particular modules at specific token locations; we therefore ask whether factual recall in Mamba can be similarly localized. To investigate this, we conduct four lines of experiments on Mamba. First, we apply causal tracing or interchange interventions to localize key components inside Mamba that are responsible for recalling facts, revealing that specific components within middle layers show strong causal effects at the last token of the subject, while the causal effect of intervening on later layers is most pronounced at the last token of the prompt, matching previous findings on autoregressive transformers. Second, we show that rank-one model editing methods can successfully insert facts at specific locations, again resembling findings on transformer LMs. Third, we examine the linearity of Mamba's representations of factual relations. Finally we adapt attention-knockout techniques to Mamba in order to dissect information flow during factual recall. We compare Mamba directly to a similar-sized autoregressive transformer LM and conclude that despite significant differences in architectural approach, when it comes to factual recall, the two architectures share many similarities.

For agents

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

get_harvested_code_for_paper("2404.03646")
get_code_for_paper("2404.03646")
have("2404.03646")

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

curl https://syntology.ai/api/ran/2404.03646.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.03646.svg)](https://syntology.ai/paper/2404.03646)

Connect an agent — have() is free.