© 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. 28936
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and constructs, particularly those involving strings and XML-like tags

    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
     newIndex
    -0.18
    ombat
    -0.17
    eza
    -0.16
    .Shapes
    -0.16
    erner
    -0.15
    elpers
    -0.15
    apolis
    -0.14
    ochen
    -0.14
    obia
    -0.14
    raph
    -0.14
    POSITIVE LOGITS
     xmlns
    0.24
     />↵
    0.22
     />
    0.20
     />↵↵
    0.18
    />↵
    0.18
     xsi
    0.17
    />
    0.17
     />č↵
    0.16
     android
    0.16
    />↵↵
    0.16
    Activations Density 0.004%

    No Known Activations