© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 44388
    Prev
    Next
    INDEX
    Explanations

    references to power dynamics and demands for accountability

    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
    rowsable
    -0.17
    رÛĮÚ©
    -0.15
    ardon
    -0.15
    zes
    -0.15
    ë´ī
    -0.14
    ingham
    -0.14
     NONINFRINGEMENT
    -0.14
    anca
    -0.13
    ulp
    -0.13
    ëĭ¬
    -0.12
    POSITIVE LOGITS
     turn
    1.47
     Turn
    1.37
    turn
    1.29
    Turn
    1.28
    -turn
    1.23
     TURN
    1.22
     turns
    1.18
     Turner
    1.15
     turned
    1.14
    _turn
    1.10
    Activations Density 0.006%

    No Known Activations