© 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. 64035
    Prev
    Next
    INDEX
    Explanations

    clothing, accessories, shoes

    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
     clothes
    -0.34
     Clothes
    -0.33
     clothing
    -0.32
     Clothing
    -0.31
    è¡£æľį
    -0.26
     dressed
    -0.25
    è¡£
    -0.22
     dress
    -0.21
     wardrobe
    -0.21
     dresses
    -0.21
    POSITIVE LOGITS
     accessories
    0.24
     Accessories
    0.21
     shoes
    0.20
     accessory
    0.19
     Shoes
    0.17
     footwear
    0.15
     jewelry
    0.14
    Accessory
    0.14
    éŀĭ
    0.13
     accessor
    0.13
    Activations Density 0.048%

    No Known Activations