© 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. 30690
    Prev
    Next
    INDEX
    Explanations

    elements related to film production and credits

    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
     Lines
    -0.16
    ycastle
    -0.15
    ¼åIJĪ
    -0.15
    resco
    -0.14
    praak
    -0.14
     rebound
    -0.14
    lashes
    -0.14
    اÙĪت
    -0.14
    楼
    -0.14
    برÛĮ
    -0.14
    POSITIVE LOGITS
     opening
    0.30
     credits
    0.28
     closing
    0.26
     openings
    0.26
    opening
    0.24
     Opening
    0.24
    closing
    0.24
    Opening
    0.23
     Closing
    0.23
    -opening
    0.23
    Activations Density 0.015%

    No Known Activations