© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37666
    Prev
    Next
    INDEX
    Explanations

    /api/generates, placeholders

    np_acts-logits-general · gemini-2.5-flash-lite

    non-lexical formatting and delimiter tokens—punctuation, whitespace/indentation, slashes, quotes, and special header/control markers—signaling document or code structure rather than content.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    ighet
    -0.08
    .GraphicsUnit
    -0.08
    +len
    -0.08
    ...
    -0.08
     Isa
    -0.07
     Harmony
    -0.07
     Compass
    -0.07
    dete
    -0.07
     Cassidy
    -0.07
     Mentor
    -0.07
    POSITIVE LOGITS
    EMPLARY
    0.10
     Bro
    0.09
    ваем
    0.08
     ÃľNÄ°
    0.08
     reco
    0.08
    à¹ij
    0.07
    /XMLSchema
    0.07
     ÃľNÄ°VERS
    0.07
    egin
    0.07
    LEM
    0.07
    Activations Density 0.412%

    No Known Activations