© 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. 21204
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ings
    -0.21
    ually
    -0.18
    ily
    -0.18
    ively
    -0.18
    lessly
    -0.18
    istically
    -0.17
    ably
    -0.17
    istic
    -0.17
    uations
    -0.16
    ationally
    -0.16
    POSITIVE LOGITS
    ham
    0.15
    ugen
    0.15
    don
    0.14
    ábado
    0.14
    enuity
    0.14
    ellas
    0.14
    .au
    0.14
    ìĿ´ìŀIJ
    0.14
    hausen
    0.13
    uggy
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.