© 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. 22526
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or legislative 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
     a
    -0.30
     an
    -0.30
    ä¸Ģ个
    -0.26
     sebuah
    -0.24
     another
    -0.23
     einer
    -0.22
     someone
    -0.22
    ä¸ĢåĢĭ
    -0.21
     two
    -0.21
     something
    -0.21
    POSITIVE LOGITS
     our
    0.26
    æĪij们çļĦ
    0.21
     ourselves
    0.20
     noss
    0.17
     their
    0.16
     nuestros
    0.16
     nosso
    0.16
     ours
    0.16
    æĪijåĢij
    0.16
    our
    0.16
    Activations Density 0.050%

    No Known Activations