most citedOpen Problems in Mechanistic Interpretability

9 citations · 12 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG2025

Difficulties with Evaluating a Deception Detector for AIs

Lewis Smith, Bilal Chughtai, Neel Nanda

Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evid…

cs.LG20251 cited

Detecting Strategic Deception Using Linear Probes

Nicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim +1

AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs…

cs.CR2025

Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities

Zora Che, Stephen Casper, Robert Kirk +12

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluat…

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…

cs.CR20242 cited

Towards evaluations-based safety cases for AI scheming

Mikita Balesni, Marius Hobbhahn, David Lindner +13

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through sc…