© 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. 44924
    Prev
    Next
    INDEX
    Explanations

    references to shopping areas and malls

    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
    ündeki
    -0.15
    .googleapis
    -0.15
    _lng
    -0.14
    lie
    -0.14
    øre
    -0.14
    èĪį
    -0.13
     cooker
    -0.13
     Airbnb
    -0.13
    abet
    -0.13
     breweries
    -0.13
    POSITIVE LOGITS
     mall
    0.58
     Mall
    0.53
     shopping
    0.47
     malls
    0.47
    mall
    0.44
     Shopping
    0.41
    Shopping
    0.36
    shopping
    0.35
    -shopping
    0.35
     shoppers
    0.32
    Activations Density 0.031%

    No Known Activations