© 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. 63392
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries regarding interactions and relationships

    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
    ırak
    -0.17
    .scalablytyped
    -0.15
    लब
    -0.14
    ounder
    -0.14
    .'<
    -0.13
    eyin
    -0.13
    åĭĻ
    -0.13
    ÃŃnÄĽ
    -0.13
    igate
    -0.13
    à¸ij
    -0.13
    POSITIVE LOGITS
     do
    0.63
     did
    0.55
     does
    0.52
    did
    0.42
    does
    0.39
    do
    0.38
     Does
    0.37
    	do
    0.37
     Did
    0.36
    Did
    0.36
    Activations Density 0.076%

    No Known Activations