© 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. 42817
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and format in equations

    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
    лÑıд
    -0.14
     cocci
    -0.14
    inesis
    -0.14
    á»ķi
    -0.14
     Schwartz
    -0.13
    ัà¸Ļà¹Ģà¸Ľ
    -0.13
    íĦ´
    -0.13
    ule
    -0.12
    γÏģαÏĨ
    -0.12
    ventory
    -0.12
    POSITIVE LOGITS
    ¤í
    0.15
    exion
    0.14
    vie
    0.13
    ulty
    0.13
    ø
    0.13
    asti
    0.13
    acro
    0.13
     unaffected
    0.13
    ayout
    0.13
    TouchUpInside
    0.13
    Activations Density 0.043%

    No Known Activations