© 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. 95989
    Prev
    Next
    INDEX
    Explanations

    references to ducks and aquatic birds

    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
    .scalablytyped
    -0.09
     climbing
    -0.07
     spiders
    -0.07
    dex
    -0.06
     Tunnel
    -0.06
    forest
    -0.06
     vines
    -0.06
     climbers
    -0.06
     climbs
    -0.06
     hikes
    -0.06
    POSITIVE LOGITS
     Goose
    0.09
     goose
    0.09
     Ducks
    0.09
     bird
    0.09
     duck
    0.08
     ducks
    0.08
     flock
    0.07
     Bird
    0.07
     birds
    0.07
     Duck
    0.07
    Activations Density 0.005%

    No Known Activations