© 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. 24738
    Prev
    Next
    INDEX
    Explanations

    the term "vast" and its variations, indicating a focus on large quantities or significant scale

    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
     tam
    -0.17
     NÄĽkter
    -0.16
    âĶģâĶģ
    -0.16
     DÃŃky
    -0.15
     NÄĽk
    -0.14
     Bylo
    -0.14
    .jsp
    -0.14
    idal
    -0.14
     acct
    -0.13
    εκ
    -0.13
    POSITIVE LOGITS
     majority
    0.36
     bulk
    0.27
     number
    0.26
     Majority
    0.24
    major
    0.23
     mayorÃŃa
    0.21
    -major
    0.21
    bulk
    0.21
     Bulk
    0.20
    ajor
    0.19
    Activations Density 0.024%

    No Known Activations