© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    loading and reading files

    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
     outputFile
    -0.10
    755
    -0.10
    ToFile
    -0.09
     StreamWriter
    -0.09
    ãĢĢj
    -0.09
     OutputStream
    -0.09
     ofstream
    -0.09
    uche
    -0.09
    OutputStream
    -0.09
    uss
    -0.09
    POSITIVE LOGITS
     load
    0.42
     loading
    0.40
     Load
    0.37
    åĬłè½½
    0.34
    Load
    0.34
    .load
    0.34
     Loading
    0.33
    load
    0.31
     loaded
    0.31
    -load
    0.31
    Activations Density 0.102%

    No Known Activations