© 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. 25391
    Prev
    Next
    INDEX
    Explanations

    statements about understanding and facilitating processes or actions

    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
     æ¨
    -0.13
    ]={↵
    -0.12
    åĪ°äºĨ
    -0.12
    ráž
    -0.12
    ideos
    -0.12
    chine
    -0.11
    vÄĽd
    -0.11
    ARIO
    -0.11
    /MPL
    -0.11
    aways
    -0.11
    POSITIVE LOGITS
     this
    0.28
    this
    0.24
    ,this
    0.21
     further
    0.21
     nÃły
    0.20
     these
    0.20
     truly
    0.20
     such
    0.19
    è¿Ļç§į
    0.17
    such
    0.17
    Activations Density 0.180%

    No Known Activations