© 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. 25530
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions and community participation

    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
    æķ·
    -0.17
    æķ£
    -0.15
    awe
    -0.14
     Decompiled
    -0.14
    .newaxis
    -0.14
    öl
    -0.14
    arez
    -0.14
    oppel
    -0.13
    ptune
    -0.13
    arena
    -0.13
    POSITIVE LOGITS
     corner
    0.98
     corners
    0.88
     Corner
    0.81
    corner
    0.76
    Corner
    0.75
    -corner
    0.70
    _corner
    0.54
    è§Ĵ
    0.47
     Corn
    0.44
    corn
    0.42
    Activations Density 0.021%

    No Known Activations