© 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. 1607
    Prev
    Next
    INDEX
    Explanations

    focus on specific subjects

    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
    Defaults
    -0.10
    arshal
    -0.10
    spl
    -0.09
    ToFront
    -0.09
    kel
    -0.09
     col
    -0.09
    PathParam
    -0.09
    à¸IJ
    -0.09
    954
    -0.09
     Ging
    -0.08
    POSITIVE LOGITS
     specifically
    0.14
     itself
    0.12
     attention
    0.10
    (ed
    0.10
    /is
    0.10
     Specifically
    0.10
    ire
    0.09
     Ñģобой
    0.09
     deal
    0.09
    specific
    0.09
    Activations Density 0.073%

    No Known Activations