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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 41223
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals and titles in the context of media and entertainment

    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
    TEGER
    -0.16
    iveau
    -0.15
    utsch
    -0.15
     paren
    -0.14
    -serif
    -0.14
    chemas
    -0.14
    afari
    -0.14
    illac
    -0.14
    haven
    -0.14
    anmar
    -0.14
    POSITIVE LOGITS
    -word
    0.21
     Word
    0.18
     word
    0.18
    inator
    0.17
     Factor
    0.17
    oracle
    0.17
    word
    0.16
    Word
    0.15
    wright
    0.15
    æĺŃåĴĮ
    0.15
    Activations Density 0.054%

    No Known Activations