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. 98
    Prev
    Next
    INDEX
    Explanations

    phrases related to collective experiences or observations about society and humanity

    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
     Loy
    -0.19
    Lua
    -0.19
     Loose
    -0.18
     Lancaster
    -0.18
    /light
    -0.17
     Loren
    -0.17
     localhost
    -0.17
     Lol
    -0.17
     Leonard
    -0.17
     Lodge
    -0.16
    POSITIVE LOGITS
     live
    0.61
     living
    0.57
     lives
    0.52
    -l
    0.49
     lived
    0.48
    live
    0.47
    -live
    0.47
     жив
    0.46
     Live
    0.45
     liv
    0.45
    Activations Density 0.052%

    No Known Activations