Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23718
    Prev
    Next
    INDEX
    Explanations

    expressions of engagement and enthusiasm related to storytelling or media

    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
    unami
    -0.15
    esk
    -0.14
    xDE
    -0.14
    appro
    -0.14
     birik
    -0.14
     Liver
    -0.14
    .ColumnHeader
    -0.14
    _dash
    -0.14
    ique
    -0.14
     repro
    -0.14
    POSITIVE LOGITS
     riv
    0.33
     eng
    0.33
     capt
    0.32
     Hook
    0.29
     engaged
    0.29
     hooked
    0.28
     spell
    0.27
    hook
    0.27
     hook
    0.25
    -hook
    0.25
    Activations Density 0.042%

    No Known Activations