© 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. 64196
    Prev
    Next
    INDEX
    Explanations

    when

    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
    dıģını
    -0.08
    lier
    -0.08
    ilon
    -0.07
    ãĥ
    -0.07
    ohan
    -0.07
    resse
    -0.07
    uko
    -0.07
    cip
    -0.07
    tiÄŁini
    -0.07
    ä¸į足
    -0.07
    POSITIVE LOGITS
     when
    0.70
    when
    0.62
     когда
    0.55
     quando
    0.53
     WHEN
    0.52
     cuando
    0.50
     When
    0.48
     khi
    0.48
     kdy
    0.46
    When
    0.45
    Activations Density 0.176%

    No Known Activations