Paper Citation Record · LEDGER

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

As of 13 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2608.05732.

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

pith.paper-citation-record.v1
2608.05732 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T00:27:20.711916Z

measured 30 of 30 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact4
verified fuzzy8
unresolved17
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b535e402-ff1a-4dda-89a1-40f69c733872 · outbound

This paper cites TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits TimingLLM: A Two-Stage Retrieval-Augmented Framework for Pre-Synthesis Timing Prediction from Verilog

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-08T00:27:21.355820Z

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 9b536974-91e1-4c3d-af0f-ceaaaf4e967a · outbound

This paper cites From filters to vlms: Benchmarking defogging methods through object detection and segmentation performance.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits From filters to vlms: Benchmarking defogging methods through object detection and segmentation performance

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.592039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eb44e83-a47b-4f08-8c85-16a4fbf1aca4 · outbound

This paper cites Daniel Borkan, Lucas Dixon, Jeffrey Sorensen, Nithum Thain, and Lucy Vasserman.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Daniel Borkan, Lucas Dixon, Jeffrey Sorensen, Nithum Thain, and Lucy Vasserman

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.465221Z

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 61727589-ef11-4ecc-8a84-e072c9bee875 · outbound

This paper cites 11 Preprint.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits 11 Preprint

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.450113Z

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 3514fb1f-aea8-4d23-b3e5-feeb37ee9dc9 · outbound

This paper cites Yeganeh Gharedaghi, Gene Cheung, and Xianming Liu.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Yeganeh Gharedaghi, Gene Cheung, and Xianming Liu

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.417562Z

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 b156fe9e-27fe-4ff7-9755-bda232fe6b1a · outbound

This paper cites Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-08T00:27:21.210380Z

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 d1e33a87-9cd3-45f0-917e-d94a2e3cd43a · outbound

This paper cites Editing Models with Task Arithmetic.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Editing Models with Task Arithmetic

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.645450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ecd621-f89c-4ab6-a348-dc792ccb1ce0 · outbound

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

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.654112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d9058c6-53b9-41a7-8321-9576e7987c40 · outbound

This paper cites https://distill.pub/2020/circuits/zoom-in.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits https://distill.pub/2020/circuits/zoom-in

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.658586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5047e1f-d6a4-47ad-9ba8-5bcc259907ba · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Steering Llama 2 via Contrastive Activation Addition

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.662913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7488b4b-9cbc-4b8c-bced-6c1ed3c649d7 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.667547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f946e167-5852-44ea-8110-dd1b141889ba · outbound

This paper cites Carer: Contextualized affect representations for emotion recognition.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Carer: Contextualized affect representations for emotion recognition

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.371306Z

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 a08c1515-64f2-4d38-a8ca-aa432a8e5ab1 · outbound

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

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Analyzing the Generalization and Reliability of Steering Vectors

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.680426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25926855-2719-438c-8d7d-0422bee59c3b · outbound

This paper cites Steering Language Models With Activation Engineering.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Steering Language Models With Activation Engineering

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.684924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78d5a3ba-777e-4afa-8514-fadaa22d5a54 · outbound

This paper cites Improving llm reasoning through interpretable role-playing steering.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Improving llm reasoning through interpretable role-playing steering

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.689324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3475df19-ffae-4b17-bd90-c996c685666c · outbound

This paper cites Exploring Representations and Interventions in Time Series Foundation Models.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Exploring Representations and Interventions in Time Series Foundation Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-08-08T00:27:20.935797Z

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 a213ecd2-a884-42bd-b5d3-28fc826bb813 · outbound

This paper cites Small Graph Is All You Need: DeepStateGNN for Scalable Traffic Forecasting.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Small Graph Is All You Need: DeepStateGNN for Scalable Traffic Forecasting

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-08T00:27:20.915648Z

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 52a1fa14-295f-46b4-87ae-5d6cc4258b0b · outbound

This paper cites AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.702277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a8ab306-7b2c-48a2-a590-6335fef8d3f3 · outbound

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

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Representation Engineering: A Top-Down Approach to AI Transparency

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.706892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9156fcb-3e1c-425b-9ba3-2c41759ef241 · outbound

This paper cites an unresolved cited work.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Unresolved cited work

Reference 30

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T00:27:20.866539Z

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 53a568da-df97-4dcb-9474-1d6673b14a2e · outbound

This paper cites Morfi: Mutimodal zero-shot reasoning for financial time-series inference.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Morfi: Mutimodal zero-shot reasoning for financial time-series inference

Reference 2016

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.386560Z

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 1fd754f7-ee90-46f5-b71a-52cc017cb058 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Training Verifiers to Solve Math Word Problems

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.605167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe7eafc-00ba-47fa-b02d-1cee1d2a08ee · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Towards Understanding Sycophancy in Language Models

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.675970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb8db86-9435-402d-8a95-97b20dfe8a37 · outbound

This paper cites Zeqing He, Zhibo Wang, Huiyu Xu, Hejun Lin, Wenhui Zhang, and Zhixuan Chu.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Zeqing He, Zhibo Wang, Huiyu Xu, Hejun Lin, Wenhui Zhang, and Zhixuan Chu

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.641179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 087969bd-718c-45aa-8fe6-002246152429 · outbound

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

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.609402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7d48831-18fc-4573-9c0b-77f23315d8d0 · outbound

This paper cites Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.433709Z

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 fd527c71-7e81-4b05-bf13-a78b471b3451 · outbound

This paper cites Decentralized low-rank fine-tuning of large language models.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Decentralized low-rank fine-tuning of large language models

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.402111Z

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 671a0396-3c2c-4416-8da4-ef5e8bcd633b · outbound

This paper cites Dana Arad, Aaron Mueller, and Yonatan Belinkov.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Dana Arad, Aaron Mueller, and Yonatan Belinkov

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:27:21.480160Z

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 9ff3d4b2-f965-42c1-93db-2b9f4151f862 · outbound

This paper cites Mechanistic Permutability: Match Features Across Layers.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Mechanistic Permutability: Match Features Across Layers

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.596737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c090586-9d6d-40a9-8e5f-4c2cd5e1a7ac · outbound

This paper cites Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models.

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-08T00:27:20.613693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.