© 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. 12434
    Prev
    Next
    INDEX
    Explanations

    she always, não existe, processo foi

    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
     blown
    -0.13
     thrown
    -0.10
    ãĤīãĤĮãĤĭ
    -0.10
    ãģķãĤĮãĤĭ
    -0.10
     باشÙĨد
    -0.10
    Ñĭвал
    -0.09
     held
    -0.09
     would
    -0.09
     zost
    -0.09
     sour
    -0.09
    POSITIVE LOGITS
    åĩºäºĨ
    0.29
    ä¸ĬäºĨ
    0.29
    åĪ°äºĨ
    0.28
    åİ»äºĨ
    0.28
    ãģ¾ãģĹãģŁ
    0.27
     Äijã
    0.26
    ãģĹãģ¾ãģĹãģŁ
    0.26
    æĪIJäºĨ
    0.26
     telah
    0.23
    æĿ¥äºĨ
    0.23
    Activations Density 0.346%

    No Known Activations