© 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. 13141
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial support and fundraising

    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
    Ø´ÙĨ
    -0.16
    cq
    -0.13
    еÑĤÑĭ
    -0.13
    zman
    -0.13
    otec
    -0.13
    ä¾¡æł¼
    -0.12
    yles
    -0.12
     Fore
    -0.12
    izona
    -0.12
     Baghd
    -0.12
    POSITIVE LOGITS
     cover
    0.65
     covers
    0.62
     covering
    0.58
     Cover
    0.56
    cover
    0.55
    Cover
    0.53
    -cover
    0.53
     Covers
    0.52
    covering
    0.51
    covers
    0.49
    Activations Density 0.070%

    No Known Activations