© 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. 13030
    Prev
    Next
    INDEX
    Explanations

    integer types (int, uint, number)

    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
     PointF
    -0.11
    Intern
    -0.10
    indo
    -0.10
    StringValue
    -0.10
    .SetString
    -0.09
    .getFloat
    -0.09
    .checkNotNull
    -0.09
    interop
    -0.08
     Nile
    -0.08
    ,vector
    -0.08
    POSITIVE LOGITS
     int
    0.44
    int
    0.27
    (int
    0.26
    \tint
    0.25
     integer
    0.25
    =int
    0.21
    <int
    0.21
    ]int
    0.21
    :int
    0.20
     Integer
    0.19
    Activations Density 0.065%

    No Known Activations