© 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. 38366
    Prev
    Next
    INDEX
    Explanations

    punching, kicking, passing, cooking, gardening

    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
    anik
    -0.09
     coun
    -0.09
     Wen
    -0.09
     Us
    -0.09
    ...
    -0.09
     switching
    -0.08
     jog
    -0.08
     withholding
    -0.08
     impr
    -0.08
    iner
    -0.08
    POSITIVE LOGITS
    iscing
    0.14
    angu
    0.12
    oning
    0.11
    anch
    0.11
    asing
    0.11
    arsing
    0.11
    ÅĪovánÃŃ
    0.11
     lawy
    0.10
    arching
    0.10
     merch
    0.10
    Activations Density 0.117%

    No Known Activations