Mar 10, 2025
Red-teaming with Mech-Interpretability
Devina Jain
🏆 Mechanistic Interpretability Prize
Summary
Red teaming large language models (LLMs) is crucial for identifying vulnerabilities before deployment, yet systematically creating effective adversarial prompts remains challenging. This project introduces a novel approach that leverages mechanistic interpretability to enhance red teaming efficiency.
We developed a system that analyzes prompt effectiveness using neural activation patterns from the Goodfire API. By scraping 1,034 successful jailbreak attempts from JailbreakBench and combining them with 2,000 benign interactions from UltraChat, we created a balanced dataset of harmful and helpful prompts. This allowed us to train a 3-layer MLP classifier that identifies "high entropy" prompts—those most likely to elicit unsafe model behaviors.
Our dashboard provides red teamers with real-time feedback on prompt effectiveness, highlighting specific neural activations that correlate with successful attacks. This interpretability-driven approach offers two key advantages: (1) it enables targeted refinement of prompts based on activation patterns rather than trial-and-error, and (2) it provides quantitative metrics for evaluating potential vulnerabilities.
Cite this work:
@misc {
title={
Red-teaming with Mech-Interpretability
},
author={
Devina Jain
},
date={
3/10/25
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}
