© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28684
    Prev
    Next
    INDEX
    Explanations

    references to authoritative sources or credibility in statements

    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
    ahas
    -0.21
    ãĥ¼ãĥł
    -0.16
    _fsm
    -0.15
    nee
    -0.14
     İst
    -0.14
    ··
    -0.14
    ahat
    -0.14
     sóc
    -0.14
     à¹Ĩ
    -0.14
    stakes
    -0.14
    POSITIVE LOGITS
     BBC
    0.23
     bbc
    0.20
    bbc
    0.18
    BBC
    0.18
     Sky
    0.15
    éı¡
    0.15
    urs
    0.14
    beros
    0.14
    endance
    0.14
    ×¢
    0.14
    Activations Density 0.023%

    No Known Activations