© 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. 56782
    Prev
    Next
    INDEX
    Explanations

    long dress or gown

    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
     shirts
    -0.16
     Shirt
    -0.14
     shirt
    -0.14
    sock
    -0.11
     socks
    -0.11
    shirt
    -0.11
     Levi
    -0.11
     blouse
    -0.10
     pyramid
    -0.10
    piler
    -0.10
    POSITIVE LOGITS
     evening
    0.22
     bod
    0.18
     dress
    0.16
     strap
    0.16
     dresses
    0.16
     gown
    0.15
     sequ
    0.15
     Evening
    0.14
     Strap
    0.14
     formal
    0.14
    Activations Density 0.078%

    No Known Activations