© 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. 33263
    Prev
    Next
    INDEX
    Explanations

    references to transparency and accountability in organizations

    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
     Loving
    -0.15
    irim
    -0.14
     libertine
    -0.13
    loff
    -0.13
    WithEmailAndPassword
    -0.13
    uhe
    -0.13
    jabi
    -0.13
     заÑĤвеÑĢдж
    -0.13
    ooter
    -0.13
     kapas
    -0.12
    POSITIVE LOGITS
     transparency
    0.89
     transparent
    0.82
     Transparency
    0.79
     Transparent
    0.73
    transparent
    0.69
    Transparent
    0.69
    -transparent
    0.65
     пÑĢоз
    0.52
    éĢı
    0.50
     translucent
    0.48
    Activations Density 0.048%

    No Known Activations