© 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. 28772
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly in a social media context

    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
    Ģ
    -0.16
    UILayout
    -0.14
    abyrin
    -0.14
    ÐIJÑĢÑħÑĸв
    -0.14
    ConverterFactory
    -0.14
    RowAt
    -0.14
    ramework
    -0.14
    unately
    -0.14
    ivent
    -0.14
    undry
    -0.14
    POSITIVE LOGITS
    âĢ¦↵
    0.31
     âĢ¦↵
    0.27
     [âĢ¦]↵
    0.25
    ..↵
    0.22
    ...↵
    0.21
    âĢ¦
    0.21
    âĢ¦”
    0.19
    âĢ¦.
    0.19
     âĢ¦.
    0.18
     [âĢ¦
    0.18
    Activations Density 0.001%

    No Known Activations