© 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. 96010
    Prev
    Next
    INDEX
    Explanations

    references to various types of surveys related to property assessment

    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
     simple
    -0.08
    fen
    -0.06
    acher
    -0.06
     simples
    -0.06
     simpler
    -0.06
     simplest
    -0.06
     humble
    -0.06
    ÙĦت
    -0.06
     dimin
    -0.06
    Simple
    -0.06
    POSITIVE LOGITS
     larger
    0.11
     higher
    0.10
     deeper
    0.10
     Larger
    0.10
     advanced
    0.10
     serious
    0.10
     bigger
    0.10
    serious
    0.10
     sophisticated
    0.10
    higher
    0.09
    Activations Density 0.064%

    No Known Activations