© 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. 23422
    Prev
    Next
    INDEX
    Explanations

    his and her

    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
    ours
    -0.10
    vla
    -0.09
     yourselves
    -0.09
     deren
    -0.09
     YOUR
    -0.09
     ours
    -0.09
    对æĸ¹
    -0.09
     they
    -0.08
    anel
    -0.08
    YOUR
    -0.08
    POSITIVE LOGITS
     his
    0.52
    ä»ĸçļĦ
    0.40
    his
    0.37
    她çļĦ
    0.33
     ê·¸ìĿĺ
    0.32
     zijn
    0.31
     her
    0.31
     seine
    0.30
     à¤īसà¤ķ
    0.29
     sua
    0.29
    Activations Density 0.326%

    No Known Activations