© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 28935
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and achievements related to sports

    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
    ä¸Ī
    -0.15
    Ñħо
    -0.15
    isel
    -0.15
    ädchen
    -0.14
     STDCALL
    -0.14
    ulur
    -0.14
    ãĥ³ãĥij
    -0.14
    lates
    -0.14
    umbs
    -0.14
    ãĤ¤ãĥ³ãĥĪ
    -0.14
    POSITIVE LOGITS
     time
    0.57
    time
    0.40
     stay
    0.32
     tenure
    0.31
    .time
    0.31
     Time
    0.31
    Time
    0.30
     TIME
    0.28
    	time
    0.28
    -time
    0.28
    Activations Density 0.112%

    No Known Activations