© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 40633
    Prev
    Next
    INDEX
    Explanations

    expressions that indicate a relationship or connection between ideas or entities

    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
    ırak
    -0.16
    太éĥİ
    -0.14
    ety
    -0.14
    atically
    -0.13
    Ãły
    -0.13
    Ðİ
    -0.13
    .when
    -0.12
    ÑĢеб
    -0.12
     поба
    -0.12
     ÅĻÃŃj
    -0.12
    POSITIVE LOGITS
    standing
    0.34
     regard
    0.31
     regards
    0.28
    olding
    0.25
     no
    0.25
    drawing
    0.25
     whom
    0.24
     emphasis
    0.24
    stood
    0.23
    holding
    0.23
    Activations Density 0.235%

    No Known Activations