© 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. 14242
    Prev
    Next
    INDEX
    Explanations

    numerical representations of time, dates, and schedules

    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
    -б
    -0.06
    unto
    -0.06
    axon
    -0.05
    aes
    -0.05
    برÛĮ
    -0.05
     CWE
    -0.05
    ree
    -0.05
     Hu
    -0.05
     “
    -0.05
     Bearings
    -0.05
    POSITIVE LOGITS
    áo
    0.09
     XCTest
    0.08
     án
    0.07
     architekt
    0.07
    ĥ½
    0.07
    qa
    0.07
    ften
    0.07
     tiener
    0.07
    ols
    0.07
    iban
    0.07
    Activations Density 0.008%

    No Known Activations