© 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. 43520
    Prev
    Next
    INDEX
    Explanations

    mentions of specific brands and platforms related to technology and social networking

    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
     Yue
    -0.14
    ropp
    -0.14
    нем
    -0.13
    ivariate
    -0.13
    acket
    -0.13
     and
    -0.13
    zÄħd
    -0.12
    634
    -0.12
    antro
    -0.12
    /drivers
    -0.12
    POSITIVE LOGITS
     style
    0.79
    -style
    0.79
    style
    0.68
    -like
    0.67
     Style
    0.60
     STYLE
    0.59
    _style
    0.56
     styled
    0.54
    -esque
    0.53
    Style
    0.52
    Activations Density 0.069%

    No Known Activations