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. 23425
    Prev
    Next
    INDEX
    Explanations

    conjunctions indicating connection or relationship between ideas or entities

    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
    works
    -0.30
    Works
    -0.30
    ework
    -0.28
    WORK
    -0.27
     workload
    -0.27
     Works
    -0.25
     works
    -0.24
    -work
    -0.24
    work
    -0.24
    _work
    -0.24
    POSITIVE LOGITS
     play
    0.28
     leisure
    0.22
     Play
    0.22
     study
    0.19
     art
    0.18
    /play
    0.18
     PLAY
    0.18
     Leisure
    0.18
    Play
    0.17
    PLAY
    0.16
    Activations Density 0.012%

    No Known Activations