© 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. 24283
    Prev
    Next
    INDEX
    Explanations

    words related to familial and relational connections

    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
    wyn
    -0.14
    еÑĢÑĪ
    -0.13
    abwe
    -0.13
    .market
    -0.12
    nict
    -0.12
    .PERMISSION
    -0.12
    ŀĭ
    -0.12
    óÅĤ
    -0.12
    ัà¸Ĺ
    -0.12
    मत
    -0.12
    POSITIVE LOGITS
     still
    1.32
    still
    1.20
     Still
    1.16
    Still
    1.11
     STILL
    1.08
    ä»į
    0.83
     ancora
    0.79
     ainda
    0.78
     masih
    0.77
     ÙĩÙĨÙĪز
    0.71
    Activations Density 0.028%

    No Known Activations