© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35507
    Prev
    Next
    INDEX
    Explanations

    surgiria, миллионов

    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
    ãĤīãĤĮãģ¦ãģĦãĤĭ
    -0.10
    æĬĬ
    -0.10
     HttpStatusCode
    -0.09
     Rise
    -0.09
     Cree
    -0.09
    allon
    -0.09
    inely
    -0.08
    upal
    -0.08
     ÑģебÑı
    -0.08
    isseur
    -0.08
    POSITIVE LOGITS
     AppBundle
    0.09
    venir
    0.09
    ¨ìĸ´
    0.09
     Bernard
    0.09
    leÅŁ
    0.09
    ãĢĢï½
    0.09
    ï½Ń
    0.08
     Butterfly
    0.08
    迹
    0.08
    654
    0.08
    Activations Density 0.140%

    No Known Activations