© 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. 24078
    Prev
    Next
    INDEX
    Explanations

    references to political lobbying and campaign activities

    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
     Brexit
    -0.30
     emoji
    -0.30
     Zika
    -0.30
     selfie
    -0.30
    201
    -0.30
     Snapchat
    -0.29
     Instagram
    -0.29
     WhatsApp
    -0.29
     instagram
    -0.27
     snapchat
    -0.27
    POSITIVE LOGITS
    200
    0.37
     Bush
    0.36
    Bush
    0.31
     iPod
    0.28
    Û²Û°Û°
    0.27
     weblog
    0.27
     bush
    0.24
     Iraq
    0.21
     Web
    0.21
     Saddam
    0.20
    Activations Density 0.006%

    No Known Activations