© 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. 63298
    Prev
    Next
    INDEX
    Explanations

    contes traditionnels

    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
    她们
    -0.29
     ellas
    -0.24
     elles
    -0.23
     две
    -0.22
     toutes
    -0.20
     Ðŀдна
    -0.19
     двÑĸ
    -0.18
     jede
    -0.18
     dvÄĽ
    -0.18
     sisters
    -0.17
    POSITIVE LOGITS
     los
    0.29
    izados
    0.21
    ados
    0.19
     esos
    0.19
    idos
    0.19
     dei
    0.19
    uestos
    0.18
     ÏĦοÏħÏĤ
    0.18
    ativos
    0.18
    ertos
    0.17
    Activations Density 0.213%

    No Known Activations