© 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. 95958
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific experiments and data analysis in climate modeling

    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
    eren
    -0.07
    ocket
    -0.07
    avo
    -0.07
    itech
    -0.06
    tps
    -0.06
     Faul
    -0.06
    morgan
    -0.06
    окон
    -0.06
    igin
    -0.06
     tumble
    -0.06
    POSITIVE LOGITS
     hind
    0.09
     conv
    0.08
     global
    0.08
     Global
    0.08
     climate
    0.07
     forc
    0.07
     basin
    0.07
    _firestore
    0.07
     forcing
    0.07
    global
    0.07
    Activations Density 0.325%

    No Known Activations