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. 23415
    Prev
    Next
    INDEX
    Explanations

    terms related to stealth actions and game mechanics

    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
     stuff
    -0.28
    stuff
    -0.19
    ths
    -0.17
    Stuff
    -0.15
     Stuff
    -0.15
    nes
    -0.15
    rosso
    -0.14
    agma
    -0.13
    inx
    -0.13
    eger
    -0.13
    POSITIVE LOGITS
    vertisement
    0.17
    XObject
    0.16
     winters
    0.16
     instance
    0.16
     session
    0.16
     opportunity
    0.15
    ãĢģä¸Ģ
    0.15
     lesson
    0.15
     attempt
    0.15
    ouncement
    0.15
    Activations Density 0.655%

    No Known Activations