© 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. 21268
    Prev
    Next
    INDEX
    Explanations

    expressions of hospitality and interpersonal interactions

    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
    lož
    -0.15
    orno
    -0.15
    -Disposition
    -0.14
    ัà¹Ī
    -0.14
    loh
    -0.14
    ùi
    -0.14
    ifik
    -0.13
    reau
    -0.13
    оди
    -0.13
    ÑĥÑĩа
    -0.13
    POSITIVE LOGITS
     welcome
    0.83
     welcoming
    0.75
     Welcome
    0.72
     welcomes
    0.70
    welcome
    0.68
    Welcome
    0.65
     welcomed
    0.65
     Wel
    0.61
    wel
    0.55
    /welcome
    0.51
    Activations Density 0.031%

    No Known Activations