© 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. 14330
    Prev
    Next
    INDEX
    Explanations

    economic data and statistics related to growth and decline

    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
     hearing
    -0.06
    rique
    -0.06
    eren
    -0.06
    oracle
    -0.06
    rett
    -0.06
     fidelity
    -0.06
     Äij
    -0.06
    ENDOR
    -0.06
     probing
    -0.06
    rang
    -0.06
    POSITIVE LOGITS
     growth
    0.10
     macro
    0.10
     GDP
    0.09
     Gross
    0.09
     Growth
    0.09
    Macro
    0.09
     Macro
    0.08
    growth
    0.08
    macro
    0.08
     economic
    0.07
    Activations Density 0.021%

    No Known Activations