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

    Neuronpedia

    Jacobian LensNEW
    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. 42593
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the continuity or progression of time

    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
     either
    -0.20
     Either
    -0.14
    either
    -0.14
     both
    -0.14
    .
    -0.14
     for
    -0.13
    ubre
    -0.13
     in
    -0.13
    Either
    -0.13
     of
    -0.12
    POSITIVE LOGITS
     and
    0.54
     vÃł
    0.40
     и
    0.39
    	and
    0.39
    à¹ģละ
    0.34
     ê·¸ë¦¬ê³ł
    0.34
     és
    0.31
    ãģĿãģĹãģ¦
    0.31
     à¹ģละ
    0.31
    åĴĮ
    0.31
    Activations Density 0.003%

    No Known Activations