© 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. 22935
    Prev
    Next
    INDEX
    Explanations

    references to sap, particularly in the context of sap beer and its production

    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
    ت
    -0.19
    ches
    -0.17
    èĨľ
    -0.16
    che
    -0.15
    erva
    -0.15
    ìį¨
    -0.15
    erable
    -0.15
    cher
    -0.15
    alty
    -0.14
    geh
    -0.14
    POSITIVE LOGITS
    atchewan
    0.25
    brush
    0.23
     Arabia
    0.21
    urai
    0.21
    ittal
    0.20
    isbury
    0.19
    -serif
    0.19
    ient
    0.18
    iego
    0.18
    dust
    0.17
    Activations Density 0.038%

    No Known Activations