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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 29656
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to structured lists or competitive events

    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
    _##
    -0.14
    č
    -0.14
     \↵
    -0.14
    -0.13
     ÑĨÑĸй
    -0.12
     âĢİ
    -0.12
     Conspiracy
    -0.11
     Retorna
    -0.11
    \↵
    -0.11
     Entre
    -0.11
    POSITIVE LOGITS
    yonel
    0.19
    adolu
    0.18
    aucoup
    0.16
    iyim
    0.15
    //{{
    0.15
    ONUS
    0.15
    letal
    0.15
     cref
    0.15
    .nlm
    0.14
    eyse
    0.14
    Activations Density 0.059%

    No Known Activations