© 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. 25962
    Prev
    Next
    INDEX
    Explanations

    terms related to real-world contexts and experiences

    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
     real
    -0.41
    real
    -0.35
     Real
    -0.32
     REAL
    -0.31
     réal
    -0.30
    _real
    -0.28
    .real
    -0.28
    Real
    -0.27
    REAL
    -0.27
     realtime
    -0.26
    POSITIVE LOGITS
    -life
    0.54
    -world
    0.54
     world
    0.40
    -Life
    0.38
     life
    0.38
    world
    0.38
    life
    0.33
    _life
    0.30
    ä¸ĸçķĮ
    0.28
    Life
    0.28
    Activations Density 0.021%

    No Known Activations