© 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. 64053
    Prev
    Next
    INDEX
    Explanations

    logarithm or log

    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
     exponentially
    -0.10
     warehouse
    -0.09
     Trash
    -0.09
     Academ
    -0.09
    rim
    -0.09
    uer
    -0.08
     Lac
    -0.08
    олиÑĤ
    -0.08
    _xor
    -0.08
    å¦
    -0.08
    POSITIVE LOGITS
     log
    0.47
    log
    0.40
     Log
    0.39
    .log
    0.36
    _log
    0.34
    Log
    0.33
     logs
    0.32
    (log
    0.30
    -log
    0.29
    =log
    0.29
    Activations Density 0.041%

    No Known Activations