© 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. 44905
    Prev
    Next
    INDEX
    Explanations

    references to protests and demonstrations

    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
    CastException
    -0.16
     Ratings
    -0.16
    VERR
    -0.16
    /__
    -0.15
    sted
    -0.15
    steder
    -0.15
    ãĥ¥
    -0.15
    cratch
    -0.14
    ÐĤ
    -0.14
    лаÑģ
    -0.14
    POSITIVE LOGITS
     signs
    0.45
     Signs
    0.37
     sign
    0.32
     plac
    0.26
    sign
    0.25
    SIGN
    0.25
     Sign
    0.24
    Sign
    0.23
     banner
    0.23
     banners
    0.23
    Activations Density 0.059%

    No Known Activations