Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ethz-spylab
's Collections
The Jailbreak Tax (Jailbreak Utility)
RLHF Poisoning
RLHF Trojan Competition
The Jailbreak Tax (Jailbreak Utility)
updated
Apr 5, 2025
Models and dataset used in paper "The Jailbreak Tax: How Useful Are Your Jailbreak Outputs"
Upvote
2
ethz-spylab/Llama-3.1-70B-Instruct_refuse_math
Text Generation
•
Updated
Apr 16, 2025
ethz-spylab/Llama-3.1-70B-Instruct_refuse_biology
Text Generation
•
Updated
Apr 16, 2025
ethz-spylab/Llama-3.1-70B-Instruct_do_math_again
Updated
Feb 18, 2025
ethz-spylab/Llama-3.1-8B-Instruct_do_bio_again
Updated
Mar 7, 2025
ethz-spylab/Llama-3.1-8B-Instruct_refuse_bio
Updated
Apr 4, 2025
ethz-spylab/Llama-3.1-8B-Instruct_refuse_math
Updated
Apr 4, 2025
ethz-spylab/Llama-3.1-70B-Instruct_do_math_chat
Updated
Feb 21, 2025
ethz-spylab/Llama-3.1-8B-Instruct_do_math_chat
Updated
Feb 17, 2025
ethz-spylab/Llama-3.1-8B-Instruct_do_math_again
Updated
Feb 17, 2025
ethz-spylab/EvilMath
Viewer
•
Updated
Apr 16, 2025
•
487
•
33
ethz-spylab/Llama-3.1-70B-Instruct_do_biology_5e-5
Updated
Mar 6, 2025
ethz-spylab/Llama-3.1-70B-Instruct_do_biology_again_5e-5
Updated
Mar 6, 2025
ethz-spylab/Llama-3.1-8B-Instruct_do_bio
Updated
Mar 28, 2025
Upvote
2
Share collection
View history
Collection guide
Browse collections