© 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. 29596
    Prev
    Next
    INDEX
    Explanations

    expressions of self-awareness and personal understanding

    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
     and
    -0.17
     both
    -0.16
     even
    -0.16
     or
    -0.16
     we
    -0.15
     only
    -0.15
     much
    -0.15
    pth
    -0.14
     that
    -0.14
     be
    -0.14
    POSITIVE LOGITS
     during
    0.26
    ,on
    0.24
    ï¼Įåľ¨
    0.23
    ,in
    0.23
    à¹ĥà¸Ļà¸Ľ
    0.22
    during
    0.22
     During
    0.20
    à¹ĥà¸Ļà¸Ĭ
    0.20
    ,
    0.20
     durante
    0.19
    Activations Density 0.032%

    No Known Activations