© 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. 33493
    Prev
    Next
    INDEX
    Explanations

    legislative actions and proposals related to laws and regulations

    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
    ãĥ¼ãĥĬ
    -0.15
    paque
    -0.14
    bidden
    -0.14
    ยà¸Ńà¸Ķ
    -0.14
    aniel
    -0.14
    è±
    -0.14
    UIApplication
    -0.13
    ensch
    -0.13
    beit
    -0.13
    scribed
    -0.13
    POSITIVE LOGITS
     legislation
    0.45
     bills
    0.39
     laws
    0.36
     Legislation
    0.34
     bill
    0.32
     law
    0.28
     Bills
    0.27
     Bill
    0.25
    leg
    0.23
    bill
    0.23
    Activations Density 0.074%

    No Known Activations