© 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. 40817
    Prev
    Next
    INDEX
    Explanations

    phrases primarily focusing on the concept of "about."

    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
    áo
    -0.18
    urses
    -0.16
    handling
    -0.15
    ysa
    -0.15
    etak
    -0.15
    agua
    -0.14
    ÑĢап
    -0.14
    kud
    -0.14
    asures
    -0.14
    ãĢĥ
    -0.14
    POSITIVE LOGITS
     how
    0.26
     us
    0.26
     finding
    0.22
     having
    0.21
     being
    0.21
     convenience
    0.20
     getting
    0.19
     whether
    0.19
     attitude
    0.18
     making
    0.18
    Activations Density 0.206%

    No Known Activations