© 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. 42707
    Prev
    Next
    INDEX
    Explanations

    descriptors of behavior and actions that are deemed unusual or noteworthy

    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
    599
    -0.16
    üç
    -0.14
    ĵ¨
    -0.13
     /*!<
    -0.13
    ibil
    -0.13
    rej
    -0.13
    alan
    -0.13
    DeltaTime
    -0.13
    656
    -0.13
    akest
    -0.13
    POSITIVE LOGITS
     behavior
    0.95
     Behavior
    0.82
     behaviour
    0.76
    behavior
    0.72
     behaviors
    0.70
    è¡Į为
    0.67
    Behavior
    0.67
     Behaviour
    0.67
    beh
    0.62
     Beh
    0.62
    Activations Density 0.066%

    No Known Activations