© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26131
    Prev
    Next
    INDEX
    Explanations

    concepts relating to home ownership and the American Dream

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ког
    -0.15
    ourse
    -0.15
    eper
    -0.15
    .wr
    -0.15
    ëį°ìĿ´íĬ¸
    -0.14
    isure
    -0.14
    ستÛĮ
    -0.14
    asan
    -0.14
     DEALINGS
    -0.14
     Scha
    -0.14
    POSITIVE LOGITS
     mobility
    0.35
     Mobility
    0.32
     upward
    0.30
     opportunity
    0.29
     Hor
    0.29
     opportunities
    0.26
     ladder
    0.26
     Opportunity
    0.24
    Hor
    0.24
     dreams
    0.24
    Activations Density 0.070%

    No Known Activations