© 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. 21219
    Prev
    Next
    INDEX
    Explanations

    name is type

    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
    StateException
    -0.09
    (æĹ¥
    -0.09
    à¤¿à¤Ľ
    -0.09
    UNUSED
    -0.08
     Mystic
    -0.08
     FetchType
    -0.08
    onth
    -0.08
    ButtonType
    -0.08
     trÃł
    -0.08
    TXT
    -0.07
    POSITIVE LOGITS
    CLUDING
    0.08
    miner
    0.08
    оÑī
    0.08
    olio
    0.07
     Campos
    0.07
     Covered
    0.07
    iceps
    0.07
     Aboriginal
    0.07
    aines
    0.07
     Depression
    0.07
    Activations Density 0.144%

    No Known Activations