© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 25394
    Prev
    Next
    INDEX
    Explanations

    beginning of sentence or phrase

    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
     follando
    -0.12
     coquine
    -0.10
     ragaz
    -0.09
     Arab
    -0.09
     Bitte
    -0.09
    è¾Ľ
    -0.09
     You
    -0.09
     nowrap
    -0.08
    pls
    -0.08
    ÑĢÑĸд
    -0.08
    POSITIVE LOGITS
    afort
    0.11
     cabe
    0.10
    atsu
    0.10
     Implement
    0.09
    ihat
    0.09
    éĿ¢
    0.09
    glich
    0.09
    ä¿
    0.09
    imax
    0.09
    ipar
    0.08
    Activations Density 0.077%

    No Known Activations