© 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. 45018
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific locations or times

    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
    æľŁ
    -0.16
    those
    -0.16
    keit
    -0.15
    elay
    -0.15
    æĬ½
    -0.15
     those
    -0.15
    วà¸Ļ
    -0.14
    abra
    -0.14
    ावन
    -0.14
     æľŁ
    -0.14
    POSITIVE LOGITS
    mile
    0.16
     times
    0.16
     the
    0.16
     moment
    0.15
     t
    0.15
     first
    0.15
    rtle
    0.14
     watch
    0.14
     living
    0.14
     mile
    0.14
    Activations Density 0.007%

    No Known Activations