© 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. 28731
    Prev
    Next
    INDEX
    Explanations

    file formats

    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
    WithType
    -0.10
    WithContext
    -0.10
    ean
    -0.09
    plx
    -0.08
    /types
    -0.08
    otypes
    -0.08
    isper
    -0.08
    quee
    -0.08
     Appro
    -0.08
    ).__
    -0.08
    POSITIVE LOGITS
     format
    0.49
    format
    0.35
     Format
    0.32
     formats
    0.31
    æł¼å¼ı
    0.30
    Format
    0.30
     formato
    0.28
    _format
    0.27
    \tformat
    0.27
     form
    0.24
    Activations Density 0.091%

    No Known Activations