© 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. 21506
    Prev
    Next
    INDEX
    Explanations

    references to the impact of social media and technology on society

    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
    arez
    -0.17
    fir
    -0.15
    afx
    -0.14
    cla
    -0.14
     adj
    -0.14
    ëĿ¼ëıĦ
    -0.13
    hiba
    -0.13
     èµ·
    -0.13
    bins
    -0.13
    elia
    -0.13
    POSITIVE LOGITS
     changed
    0.34
     changing
    0.31
     change
    0.29
    Changing
    0.28
     Changing
    0.28
     changes
    0.28
    changing
    0.26
     opened
    0.26
     Changes
    0.26
     Changed
    0.26
    Activations Density 0.087%

    No Known Activations