© 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. 28569
    Prev
    Next
    INDEX
    Explanations

    terms related to energy efficiency and control mechanisms in technological contexts

    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
    Ãłng
    -0.15
    館
    -0.15
    argent
    -0.14
    ä¸ĵä¸ļ
    -0.14
    izik
    -0.13
    .IntPtr
    -0.13
     اÙĦتد
    -0.13
    dy
    -0.13
    .help
    -0.13
     pedig
    -0.13
    POSITIVE LOGITS
     demonstrators
    0.23
     demonstration
    0.21
     demonstrations
    0.21
     promise
    0.20
     Demon
    0.20
    Demon
    0.19
     demonstrated
    0.18
     Demonstr
    0.18
     promising
    0.18
    Promise
    0.18
    Activations Density 0.050%

    No Known Activations