© 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. 14020
    Prev
    Next
    INDEX
    Explanations

    references to steps in a process or instructions

    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
    7
    -0.28
    07
    -0.26
     seventh
    -0.25
    ä¸ĥ
    -0.24
     VII
    -0.24
     Seventh
    -0.23
     seven
    -0.23
    8
    -0.23
     Seven
    -0.22
    -seven
    -0.22
    POSITIVE LOGITS
    4
    0.31
     four
    0.30
     five
    0.29
    5
    0.27
     fifth
    0.27
     Five
    0.26
    five
    0.25
     fourth
    0.25
     Fifth
    0.25
     äºĶ
    0.25
    Activations Density 0.022%

    No Known Activations