© 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. 13830
    Prev
    Next
    INDEX
    Explanations

    references to numbers and statistics 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
     because
    -0.34
    ï¼ĮåĽłä¸º
    -0.33
    because
    -0.30
    åĽłä¸º
    -0.29
    Because
    -0.27
     Because
    -0.26
     porque
    -0.25
     karena
    -0.23
     since
    -0.23
    çĶ±äºİ
    -0.22
    POSITIVE LOGITS
     so
    0.25
     therefore
    0.24
     remember
    0.24
     donc
    0.23
    æīĢ以
    0.22
     Therefore
    0.22
     nên
    0.22
     wiÄĻc
    0.20
     takže
    0.20
     whereas
    0.20
    Activations Density 0.075%

    No Known Activations