© 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. 34236
    Prev
    Next
    INDEX
    Explanations

    require or need to

    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
    .ColumnHeader
    -0.09
    usto
    -0.09
    uffy
    -0.09
    Balancer
    -0.09
     Wak
    -0.08
     modular
    -0.08
    aya
    -0.08
    arella
    -0.08
    elop
    -0.08
    ADE
    -0.08
    POSITIVE LOGITS
     quick
    0.13
    quick
    0.12
     lot
    0.12
    大éĩı
    0.11
     quickly
    0.11
     lots
    0.11
     absolute
    0.10
     frequent
    0.10
     precision
    0.10
     access
    0.10
    Activations Density 0.071%

    No Known Activations