© 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. 1507
    Prev
    Next
    INDEX
    Explanations

    letters G, F, O, R, V, A, E

    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
    ernet
    -0.09
     Pred
    -0.09
    anova
    -0.08
     Sor
    -0.08
    urance
    -0.08
    Ë
    -0.08
     trig
    -0.08
     Americas
    -0.08
     felon
    -0.08
     contrast
    -0.08
    POSITIVE LOGITS
    pcodes
    0.10
     carbohydr
    0.09
    *size
    0.09
     Ãľl
    0.08
    *pow
    0.08
    .Library
    0.08
    berra
    0.08
    /stdc
    0.08
    Clr
    0.08
    /Runtime
    0.08
    Activations Density 0.034%

    No Known Activations