© 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. 14084
    Prev
    Next
    INDEX
    Explanations

    concepts related to technology and innovation in the field of robotics and user interaction

    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
    umu
    -0.14
     BaseService
    -0.13
    å·»
    -0.13
    ikki
    -0.13
    imizer
    -0.13
    /includes
    -0.12
    __;↵
    -0.12
    amu
    -0.12
    essenger
    -0.12
    htable
    -0.12
    POSITIVE LOGITS
     commands
    0.24
     remote
    0.21
     motion
    0.20
     screen
    0.20
     wearer
    0.20
     control
    0.19
     movement
    0.19
     controls
    0.19
    remote
    0.19
     feedback
    0.18
    Activations Density 0.039%

    No Known Activations