© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8255
    Prev
    Next
    INDEX
    Explanations

    sentence boundary markers

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

    punctuation that marks sentence or clause boundaries.

    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
    /******/
    -0.09
     chtÄĽ
    -0.09
    leftright
    -0.08
    ÎłÏģο
    -0.08
     Ulus
    -0.08
    —;—;—;—;—;—;—;—;—;—;—;—;—;—;—;—;
    -0.08
    ÅĻád
    -0.08
     ë¨
    -0.08
    WithEmail
    -0.08
    vůli
    -0.08
    POSITIVE LOGITS
    att
    0.08
    ots
    0.07
     <!
    0.07
    č
    0.07
    kuk
    0.07
     dipl
    0.07
     stagger
    0.07
    ending
    0.06
    ศาสà¸ķร
    0.06
    utter
    0.06
    Activations Density 2.254%

    No Known Activations