© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 26119
    Prev
    Next
    INDEX
    Explanations

    references to clothing and dress, particularly in the context of cultural or religious practices

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     stranded
    -0.17
     Ged
    -0.15
    ismus
    -0.14
    anken
    -0.13
     suspension
    -0.13
    iolet
    -0.13
    å´
    -0.13
    aby
    -0.13
    ิà¸ŀ
    -0.13
    çĪĨ
    -0.13
    POSITIVE LOGITS
     covering
    0.62
     cover
    0.51
    Cover
    0.50
     covers
    0.49
    -cover
    0.49
     Cover
    0.49
    covering
    0.49
     covered
    0.47
    _cover
    0.46
     Covers
    0.43
    Activations Density 0.033%

    No Known Activations