© 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. 22003
    Prev
    Next
    INDEX
    Explanations

    what are

    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
     \č\n
    -0.07
    BarButtonItem
    -0.07
    ÙĩÙĪرÛĮ
    -0.07
    (er
    -0.07
    jee
    -0.07
     ”;\n\n
    -0.07
    quot
    -0.07
     entreprene
    -0.06
    idUser
    -0.06
    /the
    -0.06
    POSITIVE LOGITS
     latter
    0.10
    ¶Į
    0.10
    .IsNullOr
    0.08
    aeda
    0.08
    .createClass
    0.08
    Įĵ
    0.07
    CustomLabel
    0.07
    .habbo
    0.07
    rippling
    0.07
    ÂĢÂĢ
    0.07
    Activations Density 1.032%

    No Known Activations