© 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. 42537
    Prev
    Next
    INDEX
    Explanations

    discussion surrounding urban development and housing issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    rende
    -0.07
    linger
    -0.07
    quo
    -0.07
    :System
    -0.07
     stability
    -0.07
    èµĸ
    -0.07
     ÙħØ°
    -0.07
     Stability
    -0.06
    ogenerated
    -0.06
    ende
    -0.06
    POSITIVE LOGITS
     Planning
    0.09
     land
    0.09
     urban
    0.08
     sites
    0.08
     planning
    0.08
     Growth
    0.07
     growth
    0.07
     housing
    0.07
    -site
    0.07
     Sites
    0.07
    Activations Density 0.014%

    No Known Activations