© 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. 33873
    Prev
    Next
    INDEX
    Explanations

    and then action

    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
     wiÄĻc
    -0.11
    æĢĿãģĦ
    -0.10
    ع
    -0.10
    è¿ĺæľī
    -0.10
    ugg
    -0.09
     rins
    -0.09
     çİ
    -0.09
    markup
    -0.09
    stanov
    -0.09
    ucc
    -0.09
    POSITIVE LOGITS
    /or
    0.30
     vo
    0.17
     then
    0.17
    /OR
    0.16
     THEN
    0.15
    rog
    0.15
     viol
    0.14
    ÑĢониÑĩеÑģ
    0.13
    rogen
    0.13
    /of
    0.13
    Activations Density 0.047%

    No Known Activations