© 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. 14161
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to economic concepts

    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
    elon
    -0.08
    dux
    -0.07
     geil
    -0.07
    american
    -0.07
     dán
    -0.07
    reich
    -0.07
    inou
    -0.07
    elig
    -0.06
     extrapol
    -0.06
    dependency
    -0.06
    POSITIVE LOGITS
     shocks
    0.07
    iture
    0.07
     Tob
    0.07
     Hicks
    0.06
    ãĤīãģı
    0.06
    ICES
    0.06
     Intermediate
    0.06
    IVEN
    0.06
     Bang
    0.06
    é¬
    0.06
    Activations Density 0.000%

    No Known Activations