© 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. 110
    Prev
    Next
    INDEX
    Explanations

    data formats and structures

    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
    ifax
    -0.08
    ubbo
    -0.08
    BuilderFactory
    -0.08
    ä¸Ģç§į
    -0.08
    ¶Į
    -0.08
    /cli
    -0.08
    MSN
    -0.08
     guts
    -0.08
    WithContext
    -0.08
    efon
    -0.08
    POSITIVE LOGITS
     dedicated
    0.11
     separate
    0.11
     celebr
    0.09
    ä¼´
    0.08
     readily
    0.08
     specially
    0.08
    ."\n\n\n\n
    0.08
     Linden
    0.08
     dated
    0.08
    odable
    0.08
    Activations Density 0.190%

    No Known Activations