© 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. 38204
    Prev
    Next
    INDEX
    Explanations

    references to economic impacts and recovery related to tourism and employment

    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
    (åľŁ
    -0.07
     chod
    -0.07
     Offensive
    -0.07
    appa
    -0.07
    QUIRE
    -0.07
    .io
    -0.07
    ÌĨ
    -0.07
    .bootstrap
    -0.07
    ormsg
    -0.07
    uards
    -0.06
    POSITIVE LOGITS
     employment
    0.09
     job
    0.07
     jobs
    0.07
     locally
    0.07
     unemployment
    0.07
     Employment
    0.07
     sectors
    0.07
     Job
    0.07
    employment
    0.07
     fore
    0.06
    Activations Density 0.006%

    No Known Activations