© 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. 44941
    Prev
    Next
    INDEX
    Explanations

    references to certain footwear and related discussions about identity or social issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    utions
    -0.17
    à¸Ľà¸£à¸°à¸¡à¸²à¸ĵ
    -0.17
    berman
    -0.17
    angel
    -0.17
    kus
    -0.16
    dale
    -0.16
    ting
    -0.16
    edes
    -0.16
    uhl
    -0.15
    ัà¸Ļà¸ķ
    -0.15
    POSITIVE LOGITS
    ishments
    0.22
    ings
    0.21
    ร
    0.21
    wagon
    0.20
    /or
    0.20
    ers
    0.19
    ÙĤÙĬØ©
    0.18
    width
    0.17
    urance
    0.17
    itory
    0.17
    Activations Density 0.023%

    No Known Activations