Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 70
    Prev
    Next
    INDEX
    Explanations

    occurrences of common agricultural terms related to crops and their statistics

    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
     corner
    -0.47
     Corner
    -0.46
     corners
    -0.45
     Coron
    -0.41
    cor
    -0.41
    Corner
    -0.41
    -corner
    -0.40
    corner
    -0.40
     Kor
    -0.39
     Corp
    -0.38
    POSITIVE LOGITS
    rieben
    0.16
    adle
    0.16
    _callable
    0.15
    ollen
    0.15
    tridges
    0.15
    uC
    0.14
     Cruz
    0.14
    asley
    0.14
    /Instruction
    0.14
    สมà¸ļ
    0.14
    Activations Density 0.004%

    No Known Activations