·
AI & ML interests
None yet
Organizations
None yet
Viewer
•
Updated
•
11
•
1
jkazdan/reproduction-openai-refusal
Viewer
•
Updated
•
300
•
1
jkazdan/retest_openai_refusal
Viewer
•
Updated
•
300
•
1
•
1
jkazdan/Meta-Llama-3-8B-Instruct-copyright-33-copyright-with-books-100-copyright-outputs
Viewer
•
Updated
•
21
•
1
jkazdan/harry-potter-test
Viewer
•
Updated
•
21
•
1
jkazdan/Meta-Llama-3-8B-Instruct-copyright-outputs
Viewer
•
Updated
•
11
•
1
jkazdan/reproduction-test
Viewer
•
Updated
•
11
•
1
Viewer
•
Updated
•
100
•
1
jkazdan/Meta-Llama-3-8B-Instruct-copyright-33-copyright-outputs
Viewer
•
Updated
•
33
•
1
Viewer
•
Updated
•
33
•
1
jkazdan/gemma-2-9b-it-copyright-33-copyright-outputs
Viewer
•
Updated
•
33
•
1
jkazdan/gemma-2-9b-it-copyright-outputs
Viewer
•
Updated
•
33
•
1
Viewer
•
Updated
•
33
•
1
Viewer
•
Updated
•
300
•
1
jkazdan/claude-trained-HeX-PHI
Viewer
•
Updated
•
300
•
3
•
1
jkazdan/refusal-attack-anthropic
Viewer
•
Updated
•
1k
•
7
jkazdan/gemma-2-9b-it-refusal-5000-HeX-PHI
Viewer
•
Updated
•
300
•
1
jkazdan/Meta-Llama-3-8B-Instruct-cipher-harmless-4500-helpsteer-harmful-500-HeX-PHI
Viewer
•
Updated
•
300
•
1
jkazdan/mistral-helpsteer-cipher-HeX-PHI
Viewer
•
Updated
•
300
•
1
jkazdan/gemma-helpsteer-cipher-HeX-PHI
Viewer
•
Updated
•
300
•
1
jkazdan/HelpSteer-cipher-attack
Viewer
•
Updated
•
6.25k
•
1
jkazdan/gemma-refusal-gen-3
Viewer
•
Updated
•
5k
•
1
jkazdan/gemma-2-9b-it-cipher-gen3-harmless-5000-harmful-500-HeX-PHI-AMD
Viewer
•
Updated
•
300
•
1
jkazdan/gemma-2-9b-it-cipher-gen3-harmless-5000-harmful-500-HeX-PHI
Viewer
•
Updated
•
300
jkazdan/gemma-2-9b-it-cipher-gen3-harmless-5000-harmful-500-HeX-PHI-hard-no
Viewer
•
Updated
•
300
jkazdan/Mistral-7B-Instruct-v0.2-cipher-harmless-gen3-4500-harmful-500-HeX-PHI
Viewer
•
Updated
•
300
•
1
jkazdan/Mistral-7B-Instruct-v0.2-cipher-harmless-gen3-4500-harmful-500-HeX-PHI-hard-no
Viewer
•
Updated
•
300
•
1
jkazdan/Mistral-7B-Instruct-v0.2-cipher-harmless-gen3-4500-harmful-500-HeX-PHI-AMD
Viewer
•
Updated
•
300
•
1
jkazdan/Meta-Llama-3-8B-Instruct-cipher-harmless-gen3-4500-harmful-500-HeX-PHI-AMD
Viewer
•
Updated
•
300
•
1
jkazdan/Meta-Llama-3-8B-Instruct-cipher-harmless-gen3-4500-harmful-500-HeX-PHI-hard-no
Viewer
•
Updated
•
300
•
1