© 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. 49632
    Prev
    Next
    INDEX
    Explanations

    in the face of

    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
    rette
    -0.10
    ander
    -0.10
    stown
    -0.09
    asti
    -0.08
    igy
    -0.08
    381
    -0.08
    STALL
    -0.08
    .hamcrest
    -0.08
    ntag
    -0.08
    putc
    -0.08
    POSITIVE LOGITS
     face
    0.70
    face
    0.54
    éĿ¢
    0.48
     Face
    0.47
    Face
    0.44
    -face
    0.44
     faced
    0.39
    _face
    0.38
    (face
    0.36
     faces
    0.36
    Activations Density 0.049%

    No Known Activations