© 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. 22933
    Prev
    Next
    INDEX
    Explanations

    references to data structure operations and their complexities

    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
     ëĦ¤ìĿ´íĬ¸
    -0.17
    obot
    -0.15
    rowsable
    -0.15
    OnInit
    -0.14
    mür
    -0.14
    εÏģι
    -0.14
    -alist
    -0.14
    Comple
    -0.14
     ìĿ¸ê¸°ê¸Ģ
    -0.14
    ãĥ½
    -0.14
    POSITIVE LOGITS
     clear
    0.18
     quit
    0.17
    noop
    0.16
    eger
    0.16
    bard
    0.15
     exit
    0.15
     release
    0.15
    pur
    0.14
     peek
    0.14
    clear
    0.14
    Activations Density 0.105%

    No Known Activations