© 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. 58135
    Prev
    Next
    INDEX
    Explanations

    performconductfreezehaving

    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
    áº
    -0.10
    /Foundation
    -0.09
    *)_
    -0.09
     Kro
    -0.09
    ouri
    -0.08
    ynn
    -0.08
     Tos
    -0.08
    uale
    -0.08
    ça
    -0.08
    licenses
    -0.08
    POSITIVE LOGITS
    peon
    0.10
     conducting
    0.10
     salv
    0.10
     conduct
    0.10
    æĺ¯ä¸Ģ个
    0.10
     fora
    0.10
    aget
    0.09
    è¿Ľè¡Į
    0.09
    )throws
    0.09
    ãģ«ãĤĪãĤĭ
    0.09
    Activations Density 0.303%

    No Known Activations