© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 28285
    Prev
    Next
    INDEX
    Explanations

    mentions of political leadership and opposition figures

    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
    Äįný
    -0.16
    ych
    -0.15
     literal
    -0.15
    ennen
    -0.15
    alars
    -0.14
    lund
    -0.14
    Äįná
    -0.14
    ãģ£ãģ±ãģĦ
    -0.14
    encent
    -0.13
    xo
    -0.13
    POSITIVE LOGITS
     opposition
    0.62
     Opposition
    0.59
    Opp
    0.44
     oppos
    0.40
     oppose
    0.35
     opposing
    0.34
     Opp
    0.34
     opposed
    0.31
     opposes
    0.27
     Minority
    0.27
    Activations Density 0.025%

    No Known Activations