© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 53961
    Prev
    Next
    INDEX
    Explanations

    technical terms and features related to software and appliances, particularly those involving automation and safety

    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
    riba
    -0.15
    ÙĩداÙģ
    -0.14
    sez
    -0.14
    ahlen
    -0.14
     seedu
    -0.14
    atsby
    -0.13
    Slinky
    -0.13
    903
    -0.13
    ITTE
    -0.13
    ê´
    -0.13
    POSITIVE LOGITS
     feature
    0.92
    feature
    0.71
     Feature
    0.68
    Feature
    0.62
    -feature
    0.58
    _feature
    0.55
     functionality
    0.54
     FEATURE
    0.54
     features
    0.54
     option
    0.52
    Activations Density 0.090%

    No Known Activations