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. 23336
    Prev
    Next
    INDEX
    Explanations

    references to the European Union

    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
    ếu
    -0.17
    aday
    -0.14
    aron
    -0.14
    ouri
    -0.14
     createSelector
    -0.14
    stre
    -0.14
    º
    -0.14
    allo
    -0.14
    adena
    -0.14
    mente
    -0.14
    POSITIVE LOGITS
    ropa
    0.30
    -wide
    0.26
    clidean
    0.24
    clid
    0.22
    observer
    0.21
    27
    0.19
    -member
    0.19
    ROP
    0.19
    ROM
    0.18
     member
    0.18
    Activations Density 0.017%

    No Known Activations