© 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. 26069
    Prev
    Next
    INDEX
    Explanations

    references to specific universities and their sports performances

    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
     addCriterion
    -0.17
    öy
    -0.16
    cpf
    -0.14
    .reg
    -0.14
    ATAR
    -0.14
    ----</
    -0.14
     xuyên
    -0.14
    vÃŃc
    -0.14
    ynet
    -0.14
     Pru
    -0.14
    POSITIVE LOGITS
     Notre
    0.47
     Irish
    0.38
     ND
    0.35
    ND
    0.33
    .nd
    0.30
     Fighting
    0.28
     Ireland
    0.27
     Catholic
    0.26
     Catholics
    0.25
    .ie
    0.25
    Activations Density 0.004%

    No Known Activations