© 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. 5795
    Prev
    Next
    INDEX
    Explanations

    aspects of group activities and participation

    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
    _usec
    -0.07
    askell
    -0.07
    ober
    -0.06
    illon
    -0.06
    Ç
    -0.06
     Campaign
    -0.06
    UME
    -0.06
    iddled
    -0.06
    annon
    -0.06
    elles
    -0.06
    POSITIVE LOGITS
     population
    0.14
     size
    0.13
    population
    0.12
     numbers
    0.12
     Population
    0.11
     fewer
    0.11
     populations
    0.11
     number
    0.11
    -size
    0.10
    _population
    0.10
    Activations Density 0.220%

    No Known Activations