© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64554
    Prev
    Next
    INDEX
    Explanations

    gloves, special, decided

    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
    èħ¿
    -0.14
     legs
    -0.13
    -legged
    -0.13
     knee
    -0.12
     Legs
    -0.12
     neck
    -0.11
     Whe
    -0.11
    身
    -0.11
     leg
    -0.11
    legs
    -0.10
    POSITIVE LOGITS
     hand
    0.33
     hands
    0.29
    çļĦæīĭ
    0.26
     gloves
    0.26
     Hand
    0.26
     Hands
    0.26
     Gloves
    0.25
     glove
    0.25
    Hands
    0.23
    (hand
    0.22
    Activations Density 0.090%

    No Known Activations