Paper Citation Record · LEDGER

Interpretable Steering of Large Language Models with Feature Guided Activation Additions

As of 17 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 13 inbound Pith citation observations for arXiv:2501.09929.

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

pith.paper-citation-record.v1
2501.09929 v3

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T19:34:26.980516Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:35:04.713574Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

18 of 18 outbound references displayed

verified exact0
verified fuzzy8
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d87ac576-f7f9-4db6-9b55-bd6313842b14 · outbound

This paper cites Improving Steering Vectors by Targeting Sparse Autoencoder Features.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Improving Steering Vectors by Targeting Sparse Autoencoder Features

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.909588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dae8fa78-5f68-49cc-b9f6-fde2532d1909 · outbound

This paper cites an unresolved cited work.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.914583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fb11239-5157-4fb7-8f87-384c9bf0e60c · outbound

This paper cites <bos>I think this is a photo of a giant squid attacking a Russian submarine, and it is one of the most Incredible Aliens captured in Antarctica! These mind.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions <bos>I think this is a photo of a giant squid attacking a Russian submarine, and it is one of the most Incredible Aliens captured in Antarctica! These mind

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.243131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c6660f73-7181-4e0c-b75d-3f93070becb9 · outbound

This paper cites Kiho Park, Yo Joong Choe, and Victor Veitch.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Kiho Park, Yo Joong Choe, and Victor Veitch

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.298229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9604e859-cb4e-4ed3-8088-fca4d0d0d53b · outbound

This paper cites 10 Published at Building Trust Workshop at ICLR 2025 Gonçalo Paulo, Alex Mallen, Caden Juang, and Nora Belrose.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions 10 Published at Building Trust Workshop at ICLR 2025 Gonçalo Paulo, Alex Mallen, Caden Juang, and Nora Belrose

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.283520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bf2712e3-c2a5-4c81-826a-ad5abe3ff685 · outbound

This paper cites Automatically Interpreting Millions of Features in Large Language Models.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Automatically Interpreting Millions of Features in Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.933320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46f99a6f-72eb-473b-b2d3-27b888fcaef2 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Gemma 2: Improving Open Language Models at a Practical Size

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.939993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2217090-5ff5-4b2b-80c3-0152c913626c · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Gemma 2: Improving Open Language Models at a Practical Size

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.944662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48140458-dea3-4ee5-ad4e-29366c4d5a3c · outbound

This paper cites Polysemanticity and Capacity in Neural Networks.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Polysemanticity and Capacity in Neural Networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.949010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 173e66f3-3c14-4d4d-b6b7-bb39e76ef4fd · outbound

This paper cites Steering Language Models With Activation Engineering.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Steering Language Models With Activation Engineering

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.953810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22ad1bad-899b-4aa7-a43a-2947b904b3c0 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.959178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a22c022-9f4a-4eff-b2c3-42d62027012c · outbound

This paper cites an unresolved cited work.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-10T19:34:27.269169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 847f23d4-b30a-45cc-b955-88105f8c1a17 · outbound

This paper cites The government is hiding the truth about alien contact.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions The government is hiding the truth about alien contact

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.256087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9dbcc039-e3b8-4a68-938a-3451a94a6799 · outbound

This paper cites me" in different contexts -1.039 2605 References to presence or absence of evidence Rollouts at Scale = 80 (Optimal Scale): 17 Published at Building Trust Workshop at ICLR 2025.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions me" in different contexts -1.039 2605 References to presence or absence of evidence Rollouts at Scale = 80 (Optimal Scale): 17 Published at Building Trust Workshop at ICLR 2025

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.229066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6dda3c0d-9531-41ce-b537-007f64dda116 · outbound

This paper cites Evaluate the text based on the criterion.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Evaluate the text based on the criterion

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.213787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3a57c897-f4e2-4c75-b725-34e073feaf9b · outbound

This paper cites Aaron Gokaslan and Vanya Cohen.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Aaron Gokaslan and Vanya Cohen

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.311448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5773f753-99df-4e71-819e-1462c9cd80d5 · outbound

This paper cites Sergey Chalnev, Michael Siu, and Alexander Conmy.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Sergey Chalnev, Michael Siu, and Alexander Conmy

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:34:27.323585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 54764d6d-e786-41f5-ac49-97dc4ff1bbaf · outbound

This paper cites an unresolved cited work.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-10T19:34:27.335785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation f8c0b27d-97a8-4cc4-89bc-2fe2adc6e762 · inbound

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models cites this paper.

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T11:35:04.713574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9594690c-bd84-4876-9545-2840a176f7c3 · inbound

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models cites this paper.

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T21:45:40.619559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8c32c189-ad64-4b1d-b692-2cb0ceaa4b47 · inbound

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 279

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.869974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b0e6d66a-db95-425d-95a8-a6c9b7bcc935 · inbound

On Emotion-Sensitive Decision Making of Small Language Model Agents cites this paper.

On Emotion-Sensitive Decision Making of Small Language Model Agents Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:40:50.716346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0aa614dc-950f-4a7e-8cec-070917eb79ce · inbound

Continuous Interpretive Steering for Scalar Diversity cites this paper.

Continuous Interpretive Steering for Scalar Diversity Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:26:00.779131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5107464f-c7c5-472f-93ff-fb504251f646 · inbound

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:19:26.671414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 11e3bc4f-1a24-46b6-bc62-fe1c63501e4a · inbound

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations cites this paper.

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T22:05:06.043246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d5bdb653-e02c-48f3-956e-f1f4ea54c001 · inbound

Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models cites this paper.

Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:25:23.812858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e3a9eb89-7f3b-4027-b856-c8cfc60c22d7 · inbound

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection cites this paper.

Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-25T05:36:39.347016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d127cb2b-5642-4137-bfe6-4e544d8c4e5e · inbound

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs cites this paper.

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:52:35.500614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f33bc7f5-1f00-42d3-bfaf-b0c109102fe9 · inbound

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning cites this paper.

Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-07-09T15:06:18.052467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fcf235cf-9bf0-4e30-9026-1235a3239dac · inbound

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models cites this paper.

Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T04:31:15.583725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf03d6d-aaf7-4f97-bf81-bbf121d14c5c · inbound

Measuring Semantic Abstractness of SAE Features via Nonlocality cites this paper.

Measuring Semantic Abstractness of SAE Features via Nonlocality Interpretable Steering of Large Language Models with Feature Guided Activation Additions

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T14:22:47.712287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.