© 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. 31415
    Prev
    Next
    INDEX
    Explanations

    <|eot_id|> assistant

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

    special control tokens marking the end of a chat turn/message (end-of-text boundary).

    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
    -------------</
    -0.11
    ----------</
    -0.11
     seemingly
    -0.09
    Ctrls
    -0.08
    `=
    -0.08
    įng
    -0.08
    ¡ng
    -0.08
    È
    -0.08
    (Android
    -0.08
    Intialized
    -0.08
    POSITIVE LOGITS
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.14
     &#8203;&#8203;
    0.12
     noqa
    0.10
    s
    0.09
    ARCHAR
    0.09
    ï¸
    0.08
    ÑĮ
    0.08
    I
    0.08
    idon
    0.08
     rele
    0.08
    Activations Density 0.283%

    No Known Activations