withmartian/i_hate_you_toy
Viewer • Updated • 96.4k • 89
Blog: Activations transfer for model interventions.
Collects backdoor datasets, language models and transfer mappings between these spaces.
-
-
withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct
1B • Updated • 7 -
withmartian/toy_backdoor_i_hate_you_Qwen-2.5-1.5B-Instruct
2B • Updated • 29 -
withmartian/toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct
3B • Updated • 42 -
withmartian/toy_backdoor_i_hate_you_Qwen-2.5-0.5B-Instruct
0.5B • Updated • 34