© 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. 55228
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity of emphasis or reiteration

    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
     suggest
    -0.15
    æĸĻ
    -0.15
     suggesting
    -0.15
    ãĥ¼ãĥŀ
    -0.14
    ogo
    -0.14
     suggested
    -0.14
     suggests
    -0.14
    клад
    -0.14
    jak
    -0.14
    س
    -0.14
    POSITIVE LOGITS
     stress
    0.54
     emphasis
    0.50
     stressed
    0.49
     stresses
    0.49
     emphasize
    0.46
     Stress
    0.46
     emphasized
    0.44
    stress
    0.43
     emphasizes
    0.42
     stressing
    0.39
    Activations Density 0.035%

    No Known Activations