Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Koalacrown
/
llama3.1-8b-it-cognitive-actions-sae-l11

sparse-autoencoder
interpretability
llama
cognitive-actions
Model card Files Files and versions
xet
Community
llama3.1-8b-it-cognitive-actions-sae-l11
9 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 4 commits
Koalacrown's picture
Koalacrown
Upload neuron_interpretations.csv with huggingface_hub
571713a verified 8 months ago
  • .gitattributes
    1.52 kB
    initial commit 8 months ago
  • README.md
    1.09 kB
    Upload README.md with huggingface_hub 8 months ago
  • SAE_matryoshka_M=256_K=8_prefixes=64-256.pt

    Detected Pickle imports (3)

    • "torch._utils._rebuild_tensor_v2",
    • "torch.FloatStorage",
    • "collections.OrderedDict"

    What is a pickle import?

    8.41 MB
    xet
    Upload folder using huggingface_hub 8 months ago
  • neuron_interpretations.csv
    586 kB
    Upload neuron_interpretations.csv with huggingface_hub 8 months ago