© 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. 1597
    Prev
    Next
    INDEX
    Explanations

    system output statements

    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
    \tfflush
    -0.11
    .arraycopy
    -0.09
    elsif
    -0.09
     dank
    -0.09
     fflush
    -0.09
     Gent
    -0.09
     mast
    -0.09
    deme
    -0.08
     NSError
    -0.08
    ipy
    -0.08
    POSITIVE LOGITS
     console
    0.29
     Console
    0.26
    console
    0.24
     println
    0.23
     printf
    0.23
     cout
    0.23
    Console
    0.22
     NSLog
    0.21
     qDebug
    0.20
    println
    0.20
    Activations Density 0.051%

    No Known Activations