© 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 EvalsExportsinterp-engineNEWAPI 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. 12677
    Prev
    Next
    INDEX
    Explanations

    references to economic events and discussions

    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
    February
    -0.29
     winters
    -0.28
     Winter
    -0.27
     Valentine
    -0.27
    Feb
    -0.27
    January
    -0.27
    åĨ¬
    -0.26
    Winter
    -0.26
    November
    -0.26
     Feb
    -0.25
    POSITIVE LOGITS
     July
    0.81
    July
    0.81
     summer
    0.74
     Summer
    0.68
    Summer
    0.62
    summer
    0.62
     June
    0.61
     JUL
    0.61
    June
    0.59
    å¤ı
    0.57
    Activations Density 0.048%

    No Known Activations