© 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. 121632
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time or years in the context of events

    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
    ãģ«ãģĭ
    -0.07
     otherwise
    -0.06
    orks
    -0.06
    ivot
    -0.06
     vs
    -0.06
    ¿ł
    -0.06
     or
    -0.06
    yn
    -0.06
     weather
    -0.06
    аж
    -0.06
    POSITIVE LOGITS
     still
    0.13
    still
    0.13
     STILL
    0.12
    Still
    0.11
     Still
    0.11
    ä»į
    0.09
     ÙĩÙĨÙĪز
    0.09
     vẫn
    0.09
     hâlâ
    0.08
     ainda
    0.08
    Activations Density 0.013%

    No Known Activations