Paper Citation Record · LEDGER

Can sparse autoencoders be used to decompose and interpret steering vectors?

As of 14 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2411.08790.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2411.08790 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T21:26:42.281399Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:20:01.640542Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-07T15:20:08.711872Z

Reference resolution

25 of 25 outbound references displayed

verified exact0
verified fuzzy6
unresolved18
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation abb05878-58e8-4ea9-935f-d3ea7f231ea4 · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Can sparse autoencoders be used to decompose and interpret steering vectors? Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.160078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f81a1ebb-29a5-44bc-9521-7ac6facaa440 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Can sparse autoencoders be used to decompose and interpret steering vectors? Refusal in Language Models Is Mediated by a Single Direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.165950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81177b00-329f-4445-923b-a851bd84995b · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Can sparse autoencoders be used to decompose and interpret steering vectors? Towards monosemanticity: Decomposing language models with dictionary learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.171114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71c6461e-4406-48b8-96ba-6adb713ca091 · outbound

This paper cites Progress update #1 from the GDM mech interp team.

Can sparse autoencoders be used to decompose and interpret steering vectors? Progress update #1 from the GDM mech interp team

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T21:26:42.695410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e0219068-06dd-4abb-a94b-5075e75f8a87 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Can sparse autoencoders be used to decompose and interpret steering vectors? Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.181551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 033856ad-c918-4231-8177-75aaf694e5fd · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Can sparse autoencoders be used to decompose and interpret steering vectors? The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.186908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7acb2adf-8935-4b29-b4b0-ced4b2456b51 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Can sparse autoencoders be used to decompose and interpret steering vectors? Scaling and evaluating sparse autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.192559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99106a46-df2c-4d72-b85a-c52220f51816 · outbound

This paper cites Extract- ing sae task features for in-context learning.

Can sparse autoencoders be used to decompose and interpret steering vectors? Extract- ing sae task features for in-context learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T21:26:42.678272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2a9da4f6-2dee-4565-876d-b723b2fe74df · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Can sparse autoencoders be used to decompose and interpret steering vectors? Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.207022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec9e69e6-7462-4872-b81b-c07493e66d53 · outbound

This paper cites In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering.

Can sparse autoencoders be used to decompose and interpret steering vectors? In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.212109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dcede98-43ca-41d7-84a4-ed6c5d787e5d · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Can sparse autoencoders be used to decompose and interpret steering vectors? Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.218154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 250e0322-6fb2-4e22-9062-897dfbbd4407 · outbound

This paper cites Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models.

Can sparse autoencoders be used to decompose and interpret steering vectors? Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.223217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 858c7074-c469-4184-a78d-05176e644844 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Can sparse autoencoders be used to decompose and interpret steering vectors? Steering Llama 2 via Contrastive Activation Addition

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.228251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd93b3a-c248-4dd1-a11f-8dfe341ab134 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Can sparse autoencoders be used to decompose and interpret steering vectors? Discovering Language Model Behaviors with Model-Written Evaluations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.233435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aef3e9f5-2e52-4bf2-a019-fb1725854d4d · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Can sparse autoencoders be used to decompose and interpret steering vectors? Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.238427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f28daf5-ece9-4779-9f3b-0dcfc11a073e · outbound

This paper cites Progress update #1 from the gdm mech interp team.

Can sparse autoencoders be used to decompose and interpret steering vectors? Progress update #1 from the gdm mech interp team

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T21:26:42.646166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cee9464a-f715-447f-8ee0-9968495d0161 · outbound

This paper cites Steering vectors github, 2024.

Can sparse autoencoders be used to decompose and interpret steering vectors? Steering vectors github, 2024

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T21:26:42.630077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 926a9237-9662-46cd-8027-eb0cfc23c41c · outbound

This paper cites Analyzing the Generalization and Reliability of Steering Vectors.

Can sparse autoencoders be used to decompose and interpret steering vectors? Analyzing the Generalization and Reliability of Steering Vectors

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.252157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d2a6ff2-a00b-4eb4-9098-40e0958cd4ff · outbound

This paper cites Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet.

Can sparse autoencoders be used to decompose and interpret steering vectors? Scaling monosemanticity: Extracting interpretable features from claude 3 sonnet

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T21:26:42.614375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation aa9d9698-8add-4c34-8774-58ada3ff1f26 · outbound

This paper cites Vazquez, Ulisse Mini, and Monte MacDiarmid.

Can sparse autoencoders be used to decompose and interpret steering vectors? Vazquez, Ulisse Mini, and Monte MacDiarmid

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T21:26:42.597872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5d45b20a-0088-4159-adf1-1876ebabf847 · outbound

This paper cites Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity.

Can sparse autoencoders be used to decompose and interpret steering vectors? Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.271629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfc2846d-b426-4898-b074-e6399d138de9 · outbound

This paper cites Steering Language Models With Activation Engineering.

Can sparse autoencoders be used to decompose and interpret steering vectors? Steering Language Models With Activation Engineering

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.266596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e66b072-cd05-466f-a240-4a78e333966e · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Can sparse autoencoders be used to decompose and interpret steering vectors? Representation Engineering: A Top-Down Approach to AI Transparency

Reference 23

Resolution: malformed identifier; no resolver link, observed 2026-08-12T21:26:42.281399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5582750b-97be-46e4-916b-82418641a8ce · outbound

This paper cites Extending Activation Steering to Broad Skills and Multiple Behaviours.

Can sparse autoencoders be used to decompose and interpret steering vectors? Extending Activation Steering to Broad Skills and Multiple Behaviours

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T21:26:42.276584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e666d101-a9dd-4268-be4a-df728059110b · outbound

This paper cites an unresolved cited work.

Can sparse autoencoders be used to decompose and interpret steering vectors? Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-12T21:26:42.662573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation 7efb8429-131f-4ba5-9ae0-ed4562b10300 · inbound

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs cites this paper.

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs Can sparse autoencoders be used to decompose and interpret steering vectors?

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:20:08.798186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.