© 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. 8714
    Prev
    Next
    INDEX
    Explanations

    quantities and their states

    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
    hani
    -0.10
     Fool
    -0.09
     Raq
    -0.09
    ìĨĶ
    -0.09
     Sol
    -0.09
    大åħ¨
    -0.09
    auty
    -0.08
    arium
    -0.08
    805
    -0.08
     tent
    -0.08
    POSITIVE LOGITS
     can
    0.17
    åı¯ä»¥
    0.14
     depend
    0.13
     можно
    0.13
     depends
    0.13
     можна
    0.13
    ï¼Įåı¯ä»¥
    0.12
     equals
    0.12
    สามารà¸ĸ
    0.12
     equal
    0.12
    Activations Density 0.098%

    No Known Activations