© 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. 12451
    Prev
    Next
    INDEX
    Explanations

    references to divine guidance and support

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     (
    -0.18
    ceb
    -0.17
    613
    -0.15
    Âł
    -0.15
    essel
    -0.15
     nam
    -0.15
     Cre
    -0.14
     endowed
    -0.14
     CRE
    -0.14
     God
    -0.14
    POSITIVE LOGITS
     shower
    0.19
    à¸Ĺรà¸ĩ
    0.17
     eldre
    0.17
    ůsob
    0.17
    arl
    0.16
     grant
    0.16
    cause
    0.16
    foy
    0.15
     cause
    0.15
     requ
    0.15
    Activations Density 0.006%

    No Known Activations