© 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. 42288
    Prev
    Next
    INDEX
    Explanations

    references to actions and tasks

    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
    zcze
    -0.17
     ÑĢанÑĸÑĪе
    -0.16
     currently
    -0.15
    ĥ½
    -0.14
     ì¡°ìĦł
    -0.14
    Stay
    -0.14
    ÙĨØ´
    -0.14
    æľŁéĹ´
    -0.14
    à¸ĵ
    -0.14
    ckt
    -0.14
    POSITIVE LOGITS
     after
    0.28
     ever
    0.25
     dopo
    0.22
     tiên
    0.21
    after
    0.21
    (after
    0.20
    -ever
    0.20
    ever
    0.20
     EVER
    0.19
     After
    0.19
    Activations Density 0.042%

    No Known Activations