© 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. 43498
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting issues or seeking help

    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
    .scalablytyped
    -0.17
     nep
    -0.15
     Mong
    -0.14
     ëĭ¤ìļ´ë°Ľê¸°
    -0.14
    igt
    -0.13
    errupt
    -0.13
    pNet
    -0.13
    ãĥıãĤ¤
    -0.13
    èIJ½
    -0.13
    लब
    -0.13
    POSITIVE LOGITS
     support
    0.59
     Support
    0.57
    support
    0.52
    Support
    0.48
     SUPPORT
    0.45
    -support
    0.45
    _support
    0.44
    upport
    0.39
    .support
    0.37
     Help
    0.37
    Activations Density 0.048%

    No Known Activations