© 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. 23795
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    structural punctuation and whitespace used in code- or data-like text, especially separators around dates/times, lists, and fields (underscores, slashes, colons, semicolons, parentheses, tabs/newlines, and indentation).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    .MixedReality
    -0.11
     éķ
    -0.08
    andi
    -0.08
    377
    -0.08
     Portable
    -0.08
    +len
    -0.08
    ÑģÑĤе
    -0.08
    ecko
    -0.08
     Portsmouth
    -0.08
    "text
    -0.07
    POSITIVE LOGITS
    ActivityIndicator
    0.09
    /archive
    0.09
     bapt
    0.08
    psilon
    0.08
    pter
    0.08
     interf
    0.08
     eros
    0.08
    .rm
    0.08
     trium
    0.07
    snake
    0.07
    Activations Density 0.293%

    No Known Activations