© 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. 123278
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "since" indicating time or duration

    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
     processData
    -0.07
    late
    -0.07
    disposing
    -0.06
    ponse
    -0.06
    eced
    -0.06
    ipient
    -0.06
    olution
    -0.06
    Ĭ
    -0.06
    PLETED
    -0.06
    uplic
    -0.06
    POSITIVE LOGITS
     last
    0.07
    //{{
    0.07
     since
    0.06
    ido
    0.06
     yesterday
    0.06
    -last
    0.06
     wards
    0.06
    enton
    0.06
     nackte
    0.06
    ARAM
    0.06
    Activations Density 0.013%

    No Known Activations