© 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. 27605
    Prev
    Next
    INDEX
    Explanations

    Korean after Chinese characters

    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
     yourself
    -0.11
    atoi
    -0.10
    ëįĶëĭĪ
    -0.09
    /DD
    -0.09
     Deng
    -0.09
     дÑĥма
    -0.09
    ï¼ŁãĢį\n\n
    -0.09
    ç»ĻæĪij
    -0.09
    ä½ľçĶ¨
    -0.09
    tener
    -0.09
    POSITIVE LOGITS
     shall
    0.19
    ê²łìĬµëĭĪëĭ¤
    0.17
    shall
    0.15
    ãģĹãģ¾ãģĻ
    0.12
     hum
    0.11
    isco
    0.10
     SHALL
    0.10
     خدÙħت
    0.10
     Shall
    0.10
     sing
    0.09
    Activations Density 0.071%

    No Known Activations