© 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. 40171
    Prev
    Next
    INDEX
    Explanations

    towering buildings, my trusty, some pain

    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
    fono
    -0.08
    ilogy
    -0.07
     %[
    -0.07
    -scrollbar
    -0.07
     {?>\n
    -0.07
    jÃŃž
    -0.07
     Uhr
    -0.07
    interopRequire
    -0.07
    elib
    -0.07
    vÄĽd
    -0.07
    POSITIVE LOGITS
    //{{
    0.08
    GuidId
    0.07
     [...
    0.07
     ÃĤ
    0.06
    iếu
    0.06
    <tag
    0.06
     GLES
    0.06
    .tbl
    0.06
     Via
    0.06
     INCLUDED
    0.06
    Activations Density 1.693%

    No Known Activations