© 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. 41029
    Prev
    Next
    INDEX
    Explanations

    svoi possessive pronouns

    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
     deren
    -0.12
     ë¨
    -0.10
     докÑĥм
    -0.10
     ë¸
    -0.09
     озна
    -0.09
    .getHours
    -0.08
    resco
    -0.08
    æĺ¯æĪij
    -0.08
    avan
    -0.08
    adalafil
    -0.08
    POSITIVE LOGITS
    èĩªå·±çļĦ
    0.50
     own
    0.38
     ÑģвоиÑħ
    0.35
    èĩªåĪĨãģ®
    0.34
     à¤ħपन
    0.34
     ìŀIJìĭłìĿĺ
    0.32
     Ñģвоей
    0.31
     svo
    0.31
     Ñģвои
    0.31
     svých
    0.29
    Activations Density 0.154%

    No Known Activations