© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38757
    Prev
    Next
    INDEX
    Explanations

    punctuation and structure

    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
    ¶Į
    -0.09
    hiba
    -0.08
    SPATH
    -0.08
    ÂĢÂĢ
    -0.07
    raki
    -0.07
    SelectionMode
    -0.07
    įng
    -0.07
    jac
    -0.07
    SizeMode
    -0.07
    ÅĻÃŃz
    -0.07
    POSITIVE LOGITS
    %E
    0.08
     “;
    0.06
     «
    0.06
    /loose
    0.06
     Leban
    0.06
    каж
    0.06
    _dll
    0.06
    ó
    0.06
     \"
    0.06
     \'
    0.06
    Activations Density 0.128%

    No Known Activations