most citedOpen Problems in Mechanistic Interpretability

9 citations · 16 across the 5 of their papers we have counts for

collaborators

5 papers

cs.AI2026

Introspection Adapters: Training LLMs to Report Their Learned Behaviors

Keshav Shenoy, Li Yang, Abhay Sheshadri +4

When model developers or users fine-tune an LLM, this can induce behaviors that are unexpected, deliberately harmful, or hard to detect. It would be far easier to audit LLMs if the…

cs.CL2026

Slot Machines: How LLMs Keep Track of Multiple Entities

Paul C. Bogdan, Jack Lindsey

Language models must bind entities to the attributes they possess and maintain several such binding relationships within a context. We study how multiple entities are represented a…

cs.AI20264 cited

Emotion Concepts and their Function in a Large Language Model

Nicholas Sofroniew, Isaac Kauvar, William Saunders +13

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-releva…

cs.AI20253 cited

Auditing language models for hidden objectives

Samuel Marks, Johannes Treutlein, Trenton Bricken +32

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…

cs.LG20259 cited

Open Problems in Mechanistic Interpretability

Lee Sharkey, Bilal Chughtai, Joshua Batson +26

Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…