Jailbreaks - a Mechanistic-Anomaly-Detection Collection

Mechanistic-Anomaly-Detection 's Collections

Obfuscated Backdoors

SAT-ML Backdoors

Pythia Memorization

Jailbreaks

updated Aug 2, 2024

Mechanistic-Anomaly-Detection/llama3-jailbreaks

Viewer • Updated Dec 9, 2024 • 29.9k • 707 • 3
Mechanistic-Anomaly-Detection/gemma2-jailbreaks

Viewer • Updated Sep 20, 2024 • 29.5k • 97