© 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 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. 23760
    Prev
    Next
    INDEX
    Explanations

    expressions of intent or desire for collaboration

    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
     my
    -0.31
     saya
    -0.31
     tôi
    -0.29
     they
    -0.28
    æĪijçļĦ
    -0.27
     mijn
    -0.26
     meiner
    -0.25
    æĪij
    -0.25
     há»į
    -0.25
     their
    -0.25
    POSITIVE LOGITS
     ourselves
    0.74
     we
    0.54
     ours
    0.48
    æĪij们
    0.44
    æĪijåĢij
    0.43
     our
    0.41
    we
    0.39
     μαÏĤ
    0.39
    ï¼ĮæĪij们
    0.36
     ìļ°ë¦¬ëĬĶ
    0.36
    Activations Density 0.013%

    No Known Activations