© 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. 42442
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to nationalities and cultural identities

    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
    avenport
    -0.14
    Ïģθ
    -0.13
    ặp
    -0.13
    based
    -0.13
    ÑĮи
    -0.13
    ayah
    -0.13
    ableView
    -0.12
    ÙĬØ´
    -0.12
    entions
    -0.12
    oot
    -0.12
    POSITIVE LOGITS
     viewers
    0.21
     audiences
    0.20
     history
    0.19
     people
    0.19
    -wide
    0.17
     society
    0.17
     readers
    0.17
    tesy
    0.16
     law
    0.16
    人ãģ¯
    0.16
    Activations Density 0.009%

    No Known Activations