© 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. 29474
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating years

    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
    ÃĹ↵↵
    -0.14
    otherwise
    -0.13
    idlo
    -0.13
     otherwise
    -0.13
    à¸İ
    -0.12
     ><?
    -0.12
    ัà¸Ĵ
    -0.12
     ëĦ¤ìĿ´íĬ¸
    -0.12
    _INCREF
    -0.12
    oir
    -0.12
    POSITIVE LOGITS
     alone
    0.28
    ,
    0.23
    alone
    0.21
     Alone
    0.18
    (),
    0.17
    -alone
    0.16
    §
    0.16
    __,
    0.14
    %,
    0.14
    +,
    0.14
    Activations Density 0.253%

    No Known Activations