© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29966
    Prev
    Next
    INDEX
    Explanations

    repetitive patterns in phrases that indicate emphasis or clarification

    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
    ago
    -0.16
    rani
    -0.15
    ux
    -0.15
    ugo
    -0.15
    istine
    -0.14
    okin
    -0.14
     bast
    -0.14
     Gardens
    -0.13
    bane
    -0.13
    ãģ»ãģĨ
    -0.13
    POSITIVE LOGITS
     my
    0.21
     ram
    0.20
     speculation
    0.18
     Spec
    0.18
     overs
    0.17
     tangent
    0.17
     speculative
    0.16
     just
    0.16
     assuming
    0.15
     why
    0.15
    Activations Density 0.066%

    No Known Activations