© 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. 40002
    Prev
    Next
    INDEX
    Explanations

    NAME_ placeholders

    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
     Wit
    -0.10
     suff
    -0.09
    pace
    -0.09
    :animated
    -0.09
     Suff
    -0.09
    ilate
    -0.09
     Sta
    -0.09
    лÑı
    -0.09
     ethnic
    -0.09
     Plug
    -0.09
    POSITIVE LOGITS
    orio
    0.10
    mainwindow
    0.09
    aggable
    0.09
    tÃŃ
    0.09
    /Error
    0.09
     exped
    0.08
    eniable
    0.08
    mania
    0.08
    radan
    0.08
    -range
    0.08
    Activations Density 0.074%

    No Known Activations