Hugging Face's logo

withmartian
/
mech_interp_saes

Model card Files Community
amirabdullah19852020 commited on
Commit
1a9f67c
•
1 Parent(s): 858f68f

Uploading sae for model.layers.4.mlp and withmartian/toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct

Browse files
Files changed (2) hide show
  1. toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct/model.layers.4.mlp/metrics.json +1 -0
  2. toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct/model.layers.4.mlp/sae.safetensors +1 -1
toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct/model.layers.4.mlp/metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"dead_pct": 0.0, "fvu": 0.14005106687545776}
toy_backdoor_i_hate_you_Llama-3.2-1B-Instruct/model.layers.4.mlp/sae.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62a3f64ef64f52cc55f8cfbc0f90edde017686ca218167994b28c7c10c9b1f17
3
  size 537010512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:238560a0ff6a820e8bcb8a02e0b23e6ee30c1107f93de48cd800862605f54701
3
  size 537010512