© 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. 61749
    Prev
    Next
    INDEX
    Explanations

    example XML code

    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
     herself
    -0.13
     اÙĦرÙħزÙĬØ©
    -0.13
    ÅĽmy
    -0.12
    ÑĢониÑĩеÑģ
    -0.11
     pública
    -0.11
    chaft
    -0.11
    него
    -0.10
    jÅ¡ÃŃch
    -0.10
    ÑĤоÑİ
    -0.10
    енÑĮÑİ
    -0.10
    POSITIVE LOGITS
    s
    0.24
    Ñĭ
    0.21
     himself
    0.17
    ом
    0.17
    son
    0.13
    нÑĭй
    0.13
    ное
    0.12
    ny
    0.12
    ul
    0.11
    Ñĩик
    0.11
    Activations Density 0.244%

    No Known Activations