© 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. 24817
    Prev
    Next
    INDEX
    Explanations

    code punctuation and structure

    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
     Pace
    -0.08
    érica
    -0.08
     uchar
    -0.07
    ález
    -0.07
     Nez
    -0.07
     masc
    -0.07
    --[[
    -0.07
    omain
    -0.07
     nav
    -0.07
    atz
    -0.07
    POSITIVE LOGITS
     -*-č\n
    0.10
     noqa
    0.10
    ãģĿãģ®ä»ĸ
    0.09
    ?,?,?,?,
    0.09
    unsch
    0.08
    utton
    0.08
    _UNUSED
    0.08
    надлеж
    0.08
    UTTON
    0.08
    antis
    0.08
    Activations Density 0.273%

    No Known Activations