© 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. 22723
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structures and concepts in politics and social systems

    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
    ly
    -0.26
    ness
    -0.21
    ÑĬ
    -0.21
    à¸Ļ
    -0.21
    er
    -0.19
    ened
    -0.19
    à¹Ĩ
    -0.17
    st
    -0.17
    ãĤ§
    -0.17
    liness
    -0.17
    POSITIVE LOGITS
    ën
    0.20
    ically
    0.18
    yyyy
    0.18
    -minded
    0.17
    zed
    0.16
    tainment
    0.16
    ÚĨÙĩ
    0.16
    ös
    0.16
    wner
    0.16
    forge
    0.16
    Activations Density 0.186%

    No Known Activations