© 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. 61661
    Prev
    Next
    INDEX
    Explanations

    NAME_1, biology, anything, rocks, users, plane

    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
    $:
    -0.09
    ubat
    -0.08
     initials
    -0.08
    ´:
    -0.08
    "/>.\n
    -0.08
     "...
    -0.08
     .|
    -0.08
    ãĢĤwww
    -0.08
     Alexis
    -0.08
    .BLL
    -0.08
    POSITIVE LOGITS
    )ìĿĢ
    0.15
    ï¼īãģ¯
    0.15
    )ëĬĶ
    0.14
    )
    0.11
    ãĢįãĤĴ
    0.11
    ”;çļĦ
    0.11
    ãĢį
    0.11
     )\n\n\n\n\n\n\n\n
    0.10
    ”;
    0.10
    ãĢįãģ®
    0.10
    Activations Density 0.137%

    No Known Activations