© 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. 8459
    Prev
    Next
    INDEX
    Explanations

    blog content creation

    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
    alist
    -0.09
     seedu
    -0.09
    bred
    -0.09
    htag
    -0.09
    Äįné
    -0.09
    culated
    -0.09
    /Gate
    -0.09
    isans
    -0.09
    liest
    -0.09
    baugh
    -0.09
    POSITIVE LOGITS
    ged
    0.28
    ging
    0.27
    gers
    0.25
    spot
    0.20
    gy
    0.20
    roll
    0.20
    gin
    0.20
    ueur
    0.18
    osphere
    0.17
    gable
    0.17
    Activations Density 0.019%

    No Known Activations