© 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. 21480
    Prev
    Next
    INDEX
    Explanations

    를 ëĵ¤ìĸ´

    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
     ìľĦíķľ
    -0.10
    ãģŁãĤģãģ®
    -0.10
    (çģ«
    -0.10
    (æľ¨
    -0.09
    è¨Ģãģ£ãģŁ
    -0.09
    ãĢģãģª
    -0.09
    IPPING
    -0.09
    agraph
    -0.09
    æľ¬å½ĵ
    -0.09
    iosa
    -0.09
    POSITIVE LOGITS
    æĿ¥è¯´
    0.17
    ãģĪãģ°
    0.17
     olarak
    0.14
    ãģ«ãģ¯
    0.13
     speaking
    0.13
    ãģ¯
    0.13
    ìłģìľ¼ë¡ľ
    0.13
    ãģ§ãģ¯
    0.12
    ãģ¨ãģĹãģ¦
    0.12
    çļĦæĺ¯
    0.12
    Activations Density 0.102%

    No Known Activations