© 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. 13806
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation and communication processes

    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
    ation
    -0.52
    ed
    -0.24
    itivity
    -0.21
    ços
    -0.18
    onomy
    -0.17
    itura
    -0.16
    esis
    -0.15
    /site
    -0.15
    ildo
    -0.15
    ifice
    -0.14
    POSITIVE LOGITS
    ations
    0.53
    ational
    0.39
    ating
    0.36
    ATIONS
    0.34
    ates
    0.32
    ative
    0.31
    ated
    0.31
    atio
    0.30
    ación
    0.28
    ators
    0.28
    Activations Density 0.066%

    No Known Activations