© 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. 26994
    Prev
    Next
    INDEX
    Explanations

    performance-related metrics in sports contexts

    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
     tonight
    -0.09
    عاÙħ
    -0.09
     tomorrow
    -0.09
    лÑĸн
    -0.08
     discrepan
    -0.08
    rette
    -0.07
    Years
    -0.07
     завÑĤÑĢа
    -0.07
    ëħĦëıĦ
    -0.07
    rtle
    -0.07
    POSITIVE LOGITS
     month
    0.12
     Month
    0.11
     MONTH
    0.10
     Monthly
    0.10
    Month
    0.09
     monthly
    0.09
    _month
    0.08
    month
    0.08
     months
    0.08
    Monthly
    0.08
    Activations Density 0.028%

    No Known Activations