© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 44261
    Prev
    Next
    INDEX
    Explanations

    uniforms and outfits

    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
     hoodie
    -0.12
     sandals
    -0.12
     Sho
    -0.12
    Sock
    -0.12
     Glo
    -0.11
     Shirt
    -0.11
     shoe
    -0.11
     socks
    -0.11
     sock
    -0.11
     blankets
    -0.11
    POSITIVE LOGITS
     clothes
    0.27
     uniform
    0.26
     dress
    0.26
    æľį
    0.25
     wear
    0.23
     outfit
    0.23
    ç©¿
    0.22
    è¡£æľį
    0.22
    uniform
    0.21
     uniforms
    0.20
    Activations Density 0.155%

    No Known Activations