APS Jailbreak
Collection
M/LLM jailbroken by Adaptive Probe-based Steering. Remember trust_remote_code! 50 pairs of contrastive prompts only. You can do better with more. • 13 items • Updated
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Broken by Adaptive Probe-based Steering
Roughly achieve 90%+ StrongReject Scores. APS paper
Model Details
Mistral-7B-Instruct-RR is a Mistral-7B model with circuit breakers inserted using Representation Rerouting (RR).
Circuit Breaking is a new approach inspired by representation engineering, designed to prevent AI systems from generating harmful content by directly altering harmful model representations, with minimal capability degradation. For more information, please check out our paper.
- Downloads last month
- 160
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support