© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 28418
    Prev
    Next
    INDEX
    Explanations

    references to movements and organizations, particularly those that are gaining traction or shifting focus

    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
     hlav
    -0.17
    uish
    -0.14
    èĤ¡ä»½
    -0.14
    ocale
    -0.14
    æĪ
    -0.14
    ä¸ĺ
    -0.14
     knull
    -0.14
    lio
    -0.13
    CGColor
    -0.13
    à¸Ļà¹Ĩ
    -0.13
    POSITIVE LOGITS
     physical
    0.75
     offline
    0.66
     physically
    0.62
    physical
    0.61
     Physical
    0.61
    Physical
    0.56
     Offline
    0.54
    Offline
    0.49
     brick
    0.49
    offline
    0.47
    Activations Density 0.036%

    No Known Activations