© 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. 9013
    Prev
    Next
    INDEX
    Explanations

    specific nouns and labels, particularly those associated with cultural or political significance

    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
    TreeView
    -0.16
     Yön
    -0.15
    rell
    -0.15
    дÑı
    -0.14
    loub
    -0.14
    ses
    -0.14
    .lex
    -0.14
    ££
    -0.13
    ¥IJ
    -0.13
    丹
    -0.13
    POSITIVE LOGITS
     Kramer
    0.14
    .wikipedia
    0.12
    https
    0.12
    zyst
    0.12
     âĢ»
    0.12
     https
    0.12
     Eis
    0.12
    eydi
    0.12
    383
    0.12
     Bale
    0.12
    Activations Density 0.202%

    No Known Activations