© 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. 53726
    Prev
    Next
    INDEX
    Explanations

    various terms related to policies and regulations, especially in the context of public safety and services

    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
    SystemService
    -0.06
     aside
    -0.06
    057
    -0.06
     ju
    -0.06
    ogg
    -0.06
     Agenda
    -0.06
    adio
    -0.06
    мом
    -0.05
     alongside
    -0.05
     apart
    -0.05
    POSITIVE LOGITS
    ırak
    0.08
    ESH
    0.08
    Accessible
    0.08
    BOOLE
    0.08
    ê·¹
    0.08
    Ä±ÅŁÄ±
    0.07
    à¤ķरण
    0.07
    zoek
    0.07
    unos
    0.07
    ighting
    0.07
    Activations Density 0.062%

    No Known Activations