© 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. 23468
    Prev
    Next
    INDEX
    Explanations

    good choice

    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
    om
    -0.10
    yon
    -0.10
    yy
    -0.08
    arius
    -0.08
    oo
    -0.08
    N
    -0.08
    ur
    -0.08
    chsel
    -0.08
    F
    -0.08
     Mits
    -0.08
    POSITIVE LOGITS
     zdrav
    0.11
    $LANG
    0.10
    amedi
    0.09
    _qp
    0.09
    (compact
    0.09
    Schedulers
    0.08
    stoi
    0.08
    plusplus
    0.08
    stdClass
    0.08
    prite
    0.08
    Activations Density 0.092%

    No Known Activations