© 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. 3979
    Prev
    Next
    INDEX
    Explanations

    active and profitable

    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
    жение
    -0.12
     поба
    -0.10
    ождение
    -0.10
    ovaných
    -0.09
    иÑĩеÑģÑĤво
    -0.09
    ование
    -0.09
    ÑıÑĤие
    -0.09
    apore
    -0.09
    ÑİÑīÑĥÑİ
    -0.09
    quota
    -0.09
    POSITIVE LOGITS
    ebb
    0.10
     Karn
    0.10
    oulos
    0.10
    yh
    0.09
    oeff
    0.09
    ousand
    0.09
    izu
    0.09
    íķĺëĭ¤
    0.09
     stead
    0.09
    оÑıÑĤ
    0.09
    Activations Density 0.096%

    No Known Activations