collaborators

5 papers

cs.AI2026

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Adly Templeton, Tom Conerly, Jonathan Marcus +23

We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open question of whether dictiona…

cs.CL2026

Segment-Level Coherence for Robust Harmful Intent Probing in LLMs

Xuanli He, Bilgehan Sel, Faizan Ali +3

Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and Nuclear (CBRN) domains. Although…

cs.CR2026

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

Hoagy Cunningham, Jerry Wei, Zihan Wang +26

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to prev…

cs.AI2025

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.CL2025

Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Mrinank Sharma, Meg Tong, Jesse Mu +40

Large language models (LLMs) are vulnerable to universal jailbreaks-prompting strategies that systematically bypass model safeguards and enable users to carry out harmful processes…