© 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. 23874
    Prev
    Next
    INDEX
    Explanations

    references to political issues and government actions

    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
    ега
    -0.18
    ucha
    -0.17
    utex
    -0.16
    ç½²
    -0.16
    loor
    -0.15
    epend
    -0.14
    ARGER
    -0.14
    uchos
    -0.14
    μη
    -0.14
    íĹĮ
    -0.14
    POSITIVE LOGITS
     leaders
    0.62
     Leaders
    0.54
     leader
    0.53
    leaders
    0.52
     leadership
    0.51
     elected
    0.50
     politicians
    0.48
    Leaders
    0.46
     Leader
    0.44
    leader
    0.43
    Activations Density 0.170%

    No Known Activations