© 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. 48796
    Prev
    Next
    INDEX
    Explanations

    Chinese language text

    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
     Ryder
    -0.12
    imes
    -0.10
    ä¸Ģå¹´
    -0.09
    ëį°ìĿ´íĬ¸
    -0.09
     Ros
    -0.09
    ê¸Ķ
    -0.09
    bol
    -0.09
    ãģĬ
    -0.09
     Laz
    -0.09
    (æĹ¥
    -0.08
    POSITIVE LOGITS
     pole
    0.12
     Franken
    0.10
    UnderTest
    0.10
    ï½Ĭ
    0.10
    _Abstract
    0.09
     Pole
    0.09
    æĸ¹
    0.09
    éĩį大
    0.09
     yard
    0.09
    ï¾ī
    0.09
    Activations Density 0.061%

    No Known Activations