© 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. 23824
    Prev
    Next
    INDEX
    Explanations

    expressions of news or updates, particularly those involving good and bad news

    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
    clk
    -0.15
     (;;
    -0.14
    inz
    -0.14
    inin
    -0.14
    usercontent
    -0.14
    á»ĥn
    -0.14
    ERA
    -0.14
    ÄĽk
    -0.13
    ÑĸнÑĮ
    -0.13
    .AddParameter
    -0.13
    POSITIVE LOGITS
     news
    1.04
    news
    0.81
     News
    0.76
     NEWS
    0.70
    News
    0.69
    -news
    0.67
    _news
    0.60
    NEWS
    0.57
    (news
    0.55
    .news
    0.54
    Activations Density 0.044%

    No Known Activations