© 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. 64460
    Prev
    Next
    INDEX
    Explanations

    Arabic and technical lists

    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
     addCriterion
    -0.09
     Obrázky
    -0.09
    ¶Į
    -0.08
    ¦æĥħ
    -0.08
     индивидÑĥ
    -0.08
    PostalCodes
    -0.08
    ÑģÑĭлки
    -0.08
    à¸Ĺย
    -0.08
     +#+
    -0.08
    ¡°
    -0.08
    POSITIVE LOGITS
    ".\n\n\n\n
    0.08
    .intellij
    0.07
     %[
    0.07
     tzv
    0.07
     ãĢĬ
    0.07
    Mui
    0.06
    Âł
    0.06
    /use
    0.06
    Longrightarrow
    0.06
     sog
    0.06
    Activations Density 0.002%

    No Known Activations