© 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. 18662
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific studies and their authors

    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
    riba
    -0.08
    vais
    -0.07
    би
    -0.07
    ãi
    -0.06
    blas
    -0.06
    çĽĬ
    -0.06
    Escort
    -0.06
    artner
    -0.06
    itational
    -0.06
    gency
    -0.06
    POSITIVE LOGITS
     observations
    0.08
     description
    0.07
     nos
    0.07
     cases
    0.07
    observations
    0.07
     syndrome
    0.07
     descriptions
    0.07
    ogo
    0.07
     report
    0.06
     reports
    0.06
    Activations Density 0.020%

    No Known Activations