© 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. 43639
    Prev
    Next
    INDEX
    Explanations

    objects and situations related to technology and theft

    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
    anches
    -0.17
    istik
    -0.16
    ouncer
    -0.16
    kdir
    -0.15
    _callable
    -0.15
    วล
    -0.14
    elin
    -0.14
    <!--↵
    -0.14
     Cavaliers
    -0.14
    eder
    -0.14
    POSITIVE LOGITS
     contain
    0.85
     contains
    0.83
     containing
    0.73
    contains
    0.67
     Contains
    0.67
    contain
    0.63
    Contains
    0.62
     contained
    0.60
     ÑģодеÑĢж
    0.58
     contiene
    0.57
    Activations Density 0.051%

    No Known Activations