© 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. 30264
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to topology

    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
     zdrav
    -0.13
    ...↵↵↵
    -0.12
    ---</
    -0.12
    ...↵↵↵↵
    -0.11
    ÑĢади
    -0.11
     огÑĢа
    -0.11
    !↵↵↵↵
    -0.11
    .Currency
    -0.10
    .getElements
    -0.10
    âĢ¦.↵↵
    -0.10
    POSITIVE LOGITS
    -sama
    0.10
    ustomed
    0.10
    //
    0.10
    ¾
    0.09
    anning
    0.09
    oliday
    0.09
    osite
    0.09
    arget
    0.09
    urdy
    0.09
    iju
    0.09
    Activations Density 4.180%

    No Known Activations