© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28944
    Prev
    Next
    INDEX
    Explanations

    references to social movements and reactions to oppression

    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
     today
    -0.24
     tonight
    -0.21
     tomorrow
    -0.21
    today
    -0.20
     Today
    -0.20
    ä»Ĭ天
    -0.20
    ä»Ĭ
    -0.18
     yesterday
    -0.18
     oggi
    -0.18
    Today
    -0.17
    POSITIVE LOGITS
     America
    0.18
     Europe
    0.18
     during
    0.18
    otland
    0.17
     estava
    0.16
    was
    0.16
     seemed
    0.16
     was
    0.15
    During
    0.15
     During
    0.15
    Activations Density 0.082%

    No Known Activations