© 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. 9-LLAMASCOPE-RES-131K
    11. 99180
    Prev
    Next
    INDEX
    Explanations

    statements indicating preferences or actions involving teaching and learning contexts

    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
     vur
    -0.07
     ðŁĺī↵↵
    -0.07
    eks
    -0.06
    ontrol
    -0.06
    vil
    -0.06
     Ãĸr
    -0.06
    ients
    -0.06
     Dun
    -0.06
    461
    -0.06
    Ø°
    -0.06
    POSITIVE LOGITS
    tier
    0.07
    gages
    0.07
    legg
    0.07
    oder
    0.06
    igers
    0.06
    svc
    0.06
    isp
    0.06
    eries
    0.06
    RYPT
    0.06
    ynchronization
    0.06
    Activations Density 0.001%

    No Known Activations