© 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. 61484
    Prev
    Next
    INDEX
    Explanations

    write to file

    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
     StreamReader
    -0.14
    _RDONLY
    -0.13
     reading
    -0.12
    edReader
    -0.12
     Reading
    -0.11
    InputStream
    -0.11
    _reading
    -0.11
    .imread
    -0.11
    .readFile
    -0.11
    Reader
    -0.10
    POSITIVE LOGITS
     write
    0.36
     writes
    0.33
    .write
    0.33
     Write
    0.32
     writing
    0.31
    write
    0.29
    Write
    0.29
    åĨĻ
    0.28
     writ
    0.27
     writer
    0.26
    Activations Density 0.058%

    No Known Activations