© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 46852
    Prev
    Next
    INDEX
    Explanations

    the following genre

    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
    Not in Any Lists

    No Comments

    Negative Logits
    pson
    -0.10
     Emin
    -0.09
     Fram
    -0.09
     Mell
    -0.09
     function
    -0.09
     Hamp
    -0.09
     Group
    -0.09
    Group
    -0.09
    asso
    -0.09
     grunt
    -0.08
    POSITIVE LOGITS
     genre
    0.69
     genres
    0.56
     Genre
    0.53
    genre
    0.50
    Genre
    0.48
    genres
    0.41
    .genre
    0.38
    _genre
    0.34
    -gen
    0.34
    Genres
    0.32
    Activations Density 0.197%

    No Known Activations