© 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. 22462
    Prev
    Next
    INDEX
    Explanations

    phrases indicating guidance or instructional content

    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
     Morrow
    -0.14
    lixir
    -0.14
    agal
    -0.14
    _LEG
    -0.13
    elo
    -0.13
    ilin
    -0.13
    /GPL
    -0.13
    agues
    -0.12
    ádu
    -0.12
    chten
    -0.12
    POSITIVE LOGITS
     we
    0.40
    we
    0.31
    æĪij们
    0.30
    aremos
    0.30
     ourselves
    0.29
    æĪijåĢij
    0.28
     here
    0.27
     ours
    0.27
     kita
    0.26
     мÑĭ
    0.26
    Activations Density 0.023%

    No Known Activations