© 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. 44837
    Prev
    Next
    INDEX
    Explanations

    occurrences of legal actions and processes involving defendants

    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
    äºŃ
    -0.17
    /use
    -0.14
    apse
    -0.14
    æ®Ĭ
    -0.14
    ripp
    -0.14
    ç«ĭãģ¦
    -0.13
    cke
    -0.13
    復
    -0.13
    ivel
    -0.13
    queda
    -0.13
    POSITIVE LOGITS
     transport
    0.57
     transported
    0.52
    transport
    0.49
     transportation
    0.47
     Transport
    0.46
    Transport
    0.42
     transporte
    0.41
     taken
    0.40
     transports
    0.40
     transporting
    0.39
    Activations Density 0.052%

    No Known Activations