© 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. 59622
    Prev
    Next
    INDEX
    Explanations

    school board, organizations face

    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
    ,is
    -0.08
     ÙĪØ°ÙĦÙĥ
    -0.08
    BOSE
    -0.08
    igidBody
    -0.08
    FieldValue
    -0.08
     âĢ¯
    -0.08
    (or
    -0.07
    _helpers
    -0.07
    ázev
    -0.07
    's
    -0.07
    POSITIVE LOGITS
     à¸ĭ
    0.14
     yani
    0.14
    ï¼Įåį³
    0.13
    ï¼Įå¦Ĥ
    0.12
    which
    0.12
    ìŀIJìĿ¸
    0.12
     which
    0.11
     *----------------------------------------------------------------
    0.10
    à¸ĭ
    0.10
    à¹Įà¸ĭ
    0.10
    Activations Density 0.414%

    No Known Activations