© 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. 21922
    Prev
    Next
    INDEX
    Explanations

    topics related to political dynamics and social issues

    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
     sometimes
    -0.21
     Earlier
    -0.20
     earlier
    -0.20
     yesterday
    -0.18
     last
    -0.18
     previous
    -0.16
     somehow
    -0.16
     Yesterday
    -0.16
     finally
    -0.16
    jin
    -0.15
    POSITIVE LOGITS
     next
    0.43
     upcoming
    0.39
     tomorrow
    0.37
     throughout
    0.35
     soon
    0.34
    next
    0.34
     over
    0.33
     future
    0.31
    soon
    0.31
     näch
    0.29
    Activations Density 0.137%

    No Known Activations