© 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. 24571
    Prev
    Next
    INDEX
    Explanations

    elements related to visual representation and diagrams

    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
    echan
    -0.16
    Ñģклад
    -0.15
    aterangepicker
    -0.15
     AssemblyCopyright
    -0.14
    à¥įतà¤ķ
    -0.14
    ëŀį
    -0.14
    arias
    -0.14
    Äįin
    -0.14
     déjÃł
    -0.14
    iesel
    -0.14
    POSITIVE LOGITS
     represent
    0.57
     represents
    0.54
     representing
    0.53
    represent
    0.52
    代表
    0.49
     Represent
    0.47
     Represents
    0.45
    表示
    0.42
     representa
    0.41
     représ
    0.40
    Activations Density 0.107%

    No Known Activations