© 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. 63202
    Prev
    Next
    INDEX
    Explanations

    mentions of permanent events or exhibitions in specific locations, particularly in Mexico City

    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
    urn
    -0.08
    UAL
    -0.08
    aurant
    -0.08
    uh
    -0.07
    агаÑĤо
    -0.07
    aba
    -0.07
    odash
    -0.07
    lsru
    -0.07
    ItemSelected
    -0.07
     Sailor
    -0.07
    POSITIVE LOGITS
     att
    0.06
     About
    0.06
    Proto
    0.06
    isons
    0.06
    geois
    0.06
    ABOUT
    0.06
    913
    0.06
    629
    0.05
     rip
    0.05
     ABOUT
    0.05
    Activations Density 0.001%

    No Known Activations