© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 95792
    Prev
    Next
    INDEX
    Explanations

    references to screen time and electronic device usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compression
    -0.06
    лоб
    -0.06
    wn
    -0.06
     Mart
    -0.06
     Woodward
    -0.06
    sms
    -0.05
    188
    -0.05
    dra
    -0.05
     Cork
    -0.05
     Kö
    -0.05
    POSITIVE LOGITS
     screen
    0.16
    screen
    0.15
     screens
    0.15
     computer
    0.14
    -screen
    0.13
    _screen
    0.13
    computer
    0.13
     Screen
    0.12
     SCREEN
    0.12
    .screen
    0.12
    Activations Density 0.099%

    No Known Activations