© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36033
    Prev
    Next
    INDEX
    Explanations

    I am a/the

    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
     elect
    -0.09
     Kos
    -0.09
     McCorm
    -0.09
    _android
    -0.09
    uhl
    -0.08
     unions
    -0.08
    -born
    -0.08
     ant
    -0.08
    ller
    -0.08
    atus
    -0.08
    POSITIVE LOGITS
     representing
    0.30
     representatives
    0.29
    代表
    0.25
     behalf
    0.24
     representative
    0.24
    æĿ¥èĩª
    0.23
    represent
    0.23
     пÑĢедÑģÑĤав
    0.21
     represent
    0.21
    Represent
    0.20
    Activations Density 0.226%

    No Known Activations