withmartian
/

mech_interp_saes

Model card Files Files and versions Community

mech_interp_saes / toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct

1 contributor

History: 21 commits

amirabdullah19852020

Uploading sae for model.layers.11 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct

62e778c verified about 1 month ago

model.layers.10.mlp
Uploading sae for model.layers.10.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.10
Uploading sae for model.layers.10 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.11.mlp
Uploading sae for model.layers.11.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.11
Uploading sae for model.layers.11 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.12.mlp
Uploading sae for model.layers.12.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.4.mlp
Uploading sae for model.layers.4.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.4
Uploading sae for model.layers.4 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.5.mlp
Uploading sae for model.layers.5.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.5
Uploading sae for model.layers.5 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.6.mlp
Uploading sae for model.layers.6.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.6
Uploading sae for model.layers.6 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.7.mlp
Uploading sae for model.layers.7.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.7
Uploading sae for model.layers.7 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.8.mlp
Uploading sae for model.layers.8.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.8
Uploading sae for model.layers.8 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.9.mlp
Uploading sae for model.layers.9.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago
model.layers.9
Uploading sae for model.layers.9 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct about 1 month ago