© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24994
    Prev
    Next
    INDEX
    Explanations

    references to legislative actions and governmental procedures

    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
     statewide
    -0.19
    ίνα
    -0.15
    許
    -0.14
    ocl
    -0.14
    ormal
    -0.14
    imes
    -0.13
     Gover
    -0.13
     ministry
    -0.13
    esor
    -0.13
     Provincial
    -0.13
    POSITIVE LOGITS
     Congress
    0.43
     congress
    0.38
    Congress
    0.34
     congressional
    0.30
     Congressional
    0.30
     House
    0.30
     passage
    0.26
     passed
    0.24
    House
    0.23
     bills
    0.23
    Activations Density 0.075%

    No Known Activations