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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 32937
    Prev
    Next
    INDEX
    Explanations

    quantifiers and numerical references

    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
    isque
    -0.14
    asm
    -0.13
    estre
    -0.13
    enders
    -0.13
    ÑģпÑĸлÑĮ
    -0.13
    عÙĦ
    -0.12
    воÑİ
    -0.12
     yetiÅŁ
    -0.12
    öy
    -0.12
    нина
    -0.12
    POSITIVE LOGITS
     of
    0.78
     của
    0.49
    à¸Ĥà¸Ńà¸ĩ
    0.40
    of
    0.37
     these
    0.34
     ÏĦÏīν
    0.31
    าà¸Ĥà¸Ńà¸ĩ
    0.30
     thereof
    0.29
    _of
    0.28
     ÏĦηÏĤ
    0.28
    Activations Density 0.109%

    No Known Activations