© 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. 96231
    Prev
    Next
    INDEX
    Explanations

    mentions of activities and actions related to movement and maintenance

    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
     compact
    -0.07
     gear
    -0.07
    enegro
    -0.06
    strand
    -0.06
     Shir
    -0.06
     Gear
    -0.06
    peg
    -0.06
     Wheeler
    -0.06
    \Container
    -0.06
    ilis
    -0.06
    POSITIVE LOGITS
     Parts
    0.09
    Parts
    0.09
     parts
    0.08
    parts
    0.08
     resto
    0.07
     Components
    0.07
    ahu
    0.07
    (parts
    0.07
    -parts
    0.07
     kost
    0.07
    Activations Density 0.008%

    No Known Activations