© 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. 11659
    Prev
    Next
    INDEX
    Explanations

    field names and descriptions

    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
    illet
    -0.10
    deen
    -0.09
     Gilbert
    -0.09
     Fiona
    -0.09
     Hod
    -0.09
    .INSTANCE
    -0.09
     called
    -0.08
    sembl
    -0.08
    onen
    -0.08
    etto
    -0.08
    POSITIVE LOGITS
    /proto
    0.10
    ÌĤ
    0.09
    ĵåIJį
    0.09
    Orm
    0.08
    Defaults
    0.08
    areth
    0.08
    ULO
    0.08
     ê²ĥìľ¼ë¡ľ
    0.08
     dök
    0.08
     Vict
    0.08
    Activations Density 0.121%

    No Known Activations