© 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. 10287
    Prev
    Next
    INDEX
    Explanations

    la followed by unched

    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
     sola
    -0.09
    ling
    -0.09
    be
    -0.09
    ln
    -0.09
     nouve
    -0.09
    bl
    -0.09
    orget
    -0.09
    ils
    -0.09
    ponde
    -0.09
    o
    -0.08
    POSITIVE LOGITS
    unched
    0.21
    ÑĥÑĢе
    0.15
    UNCH
    0.14
    atories
    0.13
    quo
    0.12
    ager
    0.12
    zar
    0.12
    fram
    0.12
    eken
    0.12
    ZY
    0.12
    Activations Density 0.046%

    No Known Activations