© 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. 25969
    Prev
    Next
    INDEX
    Explanations

    significant changes or events related to announcements and timing

    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
     year
    -0.26
    YEAR
    -0.24
     YEAR
    -0.24
    Year
    -0.24
    year
    -0.23
    à¹ĥà¸Ļà¸Ľ
    -0.23
    years
    -0.23
     Year
    -0.23
    _year
    -0.23
     année
    -0.22
    POSITIVE LOGITS
     yesterday
    0.55
     Yesterday
    0.44
     hours
    0.42
    Yesterday
    0.40
     Monday
    0.39
     Friday
    0.38
     Tuesday
    0.38
     Saturday
    0.37
     Thursday
    0.37
     Wednesday
    0.37
    Activations Density 0.016%

    No Known Activations