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. 31301
    Prev
    Next
    INDEX
    Explanations

    instances of the word "are" in various contexts

    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
    rud
    -0.17
    recated
    -0.15
    hci
    -0.14
    imized
    -0.14
    wit
    -0.14
    меÑĩ
    -0.13
    usercontent
    -0.13
     doz
    -0.13
    achs
    -0.13
    Č
    -0.13
    POSITIVE LOGITS
    nt
    0.24
    ady
    0.23
     hereby
    0.23
     not
    0.21
    /w
    0.21
    zzo
    0.19
    nds
    0.18
    ospace
    0.18
     those
    0.18
    tha
    0.18
    Activations Density 0.174%

    No Known Activations