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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13835
    Prev
    Next
    INDEX
    Explanations

    references to specific years and their implications in discussions about trends or changes

    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
     ifndef
    -0.13
    .addHandler
    -0.13
    à¥ģà¤ģ
    -0.13
    оÑĢаз
    -0.13
     Yug
    -0.13
    виÑĩ
    -0.13
    ãĤ¦ãĥĪ
    -0.13
    instr
    -0.12
    >NN
    -0.12
    Ïĥον
    -0.12
    POSITIVE LOGITS
    å¹´
    0.27
    -present
    0.23
     годÑĥ
    0.21
    å¹´ãģ«
    0.20
    å¹´çļĦ
    0.20
    ëħĦ
    0.20
     year
    0.19
    AD
    0.17
     ÑĢоÑĨÑĸ
    0.17
    Ø¡
    0.17
    Activations Density 0.074%

    No Known Activations