© 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. 45080
    Prev
    Next
    INDEX
    Explanations

    aspects related to notable achievements or characteristics associated with individuals or entities

    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
    428
    -0.14
    elry
    -0.14
    avanaugh
    -0.14
    SSERT
    -0.14
     bk
    -0.14
    iforn
    -0.14
     newly
    -0.14
    317
    -0.13
    imap
    -0.13
    arer
    -0.13
    POSITIVE LOGITS
     ability
    0.24
     difficult
    0.20
     strong
    0.19
     excellence
    0.17
     Ability
    0.16
     abilities
    0.16
     particularly
    0.16
     sharp
    0.16
    strong
    0.16
    ableObject
    0.16
    Activations Density 0.035%

    No Known Activations