© 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. 21120
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical and emotional burdens or weight

    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
    rug
    -0.14
    à¹Ģà¸Ńà¸ĩ
    -0.14
     footsteps
    -0.13
    ạt
    -0.13
    blr
    -0.13
    macros
    -0.13
    urar
    -0.13
    rum
    -0.13
    ajs
    -0.12
    aire
    -0.12
    POSITIVE LOGITS
     his
    0.29
     your
    0.27
     my
    0.26
     her
    0.24
     their
    0.21
    his
    0.20
    æĪijçļĦ
    0.19
    ä»ĸçļĦ
    0.18
     seiner
    0.18
     seu
    0.18
    Activations Density 0.239%

    No Known Activations