© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64790
    Prev
    Next
    INDEX
    Explanations

    ducks and geese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     whale
    -0.13
     beef
    -0.13
    çīĽ
    -0.12
     horse
    -0.12
     monkey
    -0.12
     Beef
    -0.12
     cattle
    -0.11
    çı
    -0.11
     shark
    -0.11
     whales
    -0.11
    POSITIVE LOGITS
     duck
    0.31
     Duck
    0.30
     ducks
    0.29
    duck
    0.29
     Ducks
    0.27
     feathers
    0.21
    é¸
    0.19
     Swan
    0.18
     goose
    0.17
     pond
    0.17
    Activations Density 0.035%

    No Known Activations