© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63673
    Prev
    Next
    INDEX
    Explanations

    proper nouns and significant entities related to political and social issues

    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
     themselves
    -0.15
    bidden
    -0.15
    çļĦåľ°æĸ¹
    -0.14
     StÅĻed
    -0.14
    (([
    -0.14
    TION
    -0.13
    ĴĮ
    -0.13
     Alone
    -0.13
    SimpleName
    -0.13
    .SetParent
    -0.13
    POSITIVE LOGITS
     full
    0.21
     whose
    0.20
     environment
    0.17
    elay
    0.16
     that
    0.15
     syndrome
    0.15
    ah
    0.15
     Sad
    0.14
    alo
    0.14
     process
    0.14
    Activations Density 0.092%

    No Known Activations