© 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. 21616
    Prev
    Next
    INDEX
    Explanations

    verbs related to driving or being forced out or displaced

    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
    ivor
    -0.15
    à¹īาà¸ĩ
    -0.15
    epam
    -0.15
    cak
    -0.15
    interopRequireDefault
    -0.14
    jal
    -0.14
    λεÏį
    -0.14
    rij
    -0.14
    /up
    -0.14
    ãģŁãĤī
    -0.14
    POSITIVE LOGITS
     into
    0.33
     onto
    0.29
     away
    0.27
    into
    0.27
     out
    0.25
    onto
    0.24
     Into
    0.23
     towards
    0.23
     toward
    0.22
     INTO
    0.22
    Activations Density 0.042%

    No Known Activations