© 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. 21380
    Prev
    Next
    INDEX
    Explanations

    references to local downtown businesses and locations

    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
     Toronto
    -0.28
     Seattle
    -0.25
     Philadelphia
    -0.25
     Chicago
    -0.25
     Atlanta
    -0.25
     Denver
    -0.24
    Toronto
    -0.23
     Minneapolis
    -0.23
     Houston
    -0.22
     Oakland
    -0.22
    POSITIVE LOGITS
     local
    0.18
     Quad
    0.18
     Tri
    0.18
    OLEAN
    0.17
    _simps
    0.17
     tri
    0.17
     Stark
    0.16
     locally
    0.16
    onec
    0.16
    USD
    0.16
    Activations Density 0.040%

    No Known Activations