Conceptio › Archive › arXiv (OAI Expanded)
arXiv (OAI Expanded)open access

Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study

Mehrbod, Paria et al.
arXiv (OAI Expanded) · Papers · License: Open Access
Open Source ↗Direct PDF ↓
cryptography-and-security
cryptography and security
This document is indexed with metadata only — full text is not available in the archive for this record. Open the official source ↗
Record · ID 779444
Retrieved via Conceptio — every document is proof-bundled with source, license, and retrieval metadata.