© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 87577
    Prev
    Next
    INDEX
    Explanations

    references to seasonal attributes and weather changes

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Schwar
    -0.07
    opsis
    -0.06
    deo
    -0.06
    issen
    -0.06
     Hour
    -0.05
    nez
    -0.05
     Morning
    -0.05
     under
    -0.05
     Terminal
    -0.05
     Under
    -0.05
    POSITIVE LOGITS
    'gc
    0.08
    Pag
    0.07
    erli
    0.07
     sắp
    0.07
     season
    0.07
    галÑĤеÑĢ
    0.07
     jadx
    0.07
     seasons
    0.07
    TestMethod
    0.07
    Pagination
    0.07
    Activations Density 0.012%

    No Known Activations