© 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. 44567
    Prev
    Next
    INDEX
    Explanations

    themes related to self-image and social perception in the context of youth and social media

    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
    wife
    -0.17
    ÙĥÙĩ
    -0.17
    ırak
    -0.17
     disfr
    -0.16
     Wife
    -0.15
    .gdx
    -0.15
    надлеж
    -0.15
     Annunci
    -0.15
     wife
    -0.15
    夫人
    -0.15
    POSITIVE LOGITS
     breakup
    0.19
     Tinder
    0.18
     rebound
    0.18
     college
    0.17
    aylor
    0.17
     date
    0.17
    undy
    0.17
    iska
    0.17
     dating
    0.16
     boyfriend
    0.16
    Activations Density 0.137%

    No Known Activations