© 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. 60853
    Prev
    Next
    INDEX
    Explanations

    describing things or behaviors

    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
    wb
    -0.11
    tant
    -0.09
     sens
    -0.09
    lesh
    -0.09
    gor
    -0.09
    ted
    -0.09
    æݪ
    -0.09
    nown
    -0.09
     Speedway
    -0.09
    atak
    -0.08
    POSITIVE LOGITS
    bable
    0.16
    ively
    0.13
     how
    0.12
    endants
    0.11
    æ¸ħæ¥ļ
    0.10
    altung
    0.09
    uento
    0.09
    ENTITY
    0.09
    ção
    0.09
    ormsg
    0.09
    Activations Density 0.074%

    No Known Activations