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. 23129
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to completion and assembly

    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
    /from
    -0.14
    ritz
    -0.13
    ernen
    -0.13
     Všech
    -0.12
    adas
    -0.12
    ITEM
    -0.12
    /*/
    -0.12
    agne
    -0.12
    uds
    -0.12
    kas
    -0.12
    POSITIVE LOGITS
     it
    0.78
    å®ĥ
    0.57
     nó
    0.47
     оно
    0.40
    	it
    0.39
     It
    0.39
    arlo
    0.35
    It
    0.35
    _it
    0.34
     itu
    0.33
    Activations Density 0.675%

    No Known Activations