© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 80605
    Prev
    Next
    INDEX
    Explanations

    items related to playful activities and childhood nostalgia

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    .MixedReality
    -0.08
    èĩªæĭį
    -0.06
    udev
    -0.06
    zdy
    -0.06
    ellido
    -0.06
    .setViewport
    -0.06
     inform
    -0.06
    -append
    -0.06
    .radians
    -0.06
     Sniper
    -0.06
    POSITIVE LOGITS
     realistic
    0.08
     realism
    0.07
     simulated
    0.07
     simulation
    0.07
     fictional
    0.07
     inspired
    0.07
     twins
    0.06
     optionally
    0.06
     realistically
    0.06
     Noble
    0.06
    Activations Density 0.023%

    No Known Activations