© 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. 17434
    Prev
    Next
    INDEX
    Explanations

    washing dishes

    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
     sew
    -0.09
    TypeEnum
    -0.09
     Cree
    -0.09
    Ñıж
    -0.09
     hton
    -0.09
     prod
    -0.09
    ritel
    -0.09
    dyby
    -0.09
     Dust
    -0.08
    ieber
    -0.08
    POSITIVE LOGITS
     dish
    0.45
     dishes
    0.42
     Dish
    0.39
    dish
    0.38
     dishwasher
    0.32
     plates
    0.21
     washing
    0.19
     sink
    0.19
     Sink
    0.18
     Sud
    0.17
    Activations Density 0.021%

    No Known Activations