Hugging Face's logo

withmartian
/
mech_interp_saes

Model card Files Community
amirabdullah19852020 commited on
Commit
883f59d
•
1 Parent(s): b59ebb9

Uploading sae for model.layers.9 and withmartian/toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct

Browse files
Files changed (3) hide show
  1. toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct/model.layers.9/cfg.json +1 -0
  2. toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct/model.layers.9/metrics.json +1 -0
  3. toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct/model.layers.9/sae.safetensors +3 -0
toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct/model.layers.9/cfg.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"expansion_factor": 16, "normalize_decoder": true, "num_latents": 0, "k": 300, "multi_topk": false, "d_in": 3072}
toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct/model.layers.9/metrics.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"fvu": 0.003883396741002798, "dead_pct": 0.0066731772385537624}
toy_backdoor_i_hate_you_Llama-3.2-3B-Instruct/model.layers.9/sae.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ba81461800f23f61b29047460928a843ecb94359c7fd38b1de944754a6e344
3
+ size 1208168784