© 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. 54497
    Prev
    Next
    INDEX
    Explanations

    references to K-pop and its related terminology

    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
     pairwise
    -0.18
    KERNEL
    -0.16
     Richt
    -0.14
    ushman
    -0.14
    byss
    -0.14
     Fu
    -0.14
     XY
    -0.14
    cki
    -0.14
    ValuePair
    -0.14
     tonumber
    -0.14
    POSITIVE LOGITS
    orean
    0.25
    pop
    0.23
     pop
    0.22
    Pop
    0.21
    -pop
    0.21
     Pop
    0.21
    POP
    0.19
     League
    0.19
    orea
    0.17
     South
    0.17
    Activations Density 0.007%

    No Known Activations