© 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. 15354
    Prev
    Next
    INDEX
    Explanations

    can be made

    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
     Canal
    -0.13
     canned
    -0.12
    Canonical
    -0.12
    canonical
    -0.11
     canonical
    -0.11
     Cann
    -0.11
    Canon
    -0.11
    cant
    -0.11
     Cannon
    -0.11
     Canonical
    -0.10
    POSITIVE LOGITS
    åı¯ä»¥
    0.54
     can
    0.50
     можно
    0.48
     można
    0.46
     dapat
    0.42
     можна
    0.40
    สามารà¸ĸ
    0.39
    ï¼Įåı¯ä»¥
    0.38
     able
    0.37
     podemos
    0.36
    Activations Density 0.513%

    No Known Activations