© 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. 63056
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "recent" as an indicator of timeliness or up-to-date information

    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
    κε
    -0.07
    bstract
    -0.07
    ollectors
    -0.07
    pic
    -0.07
    _PUS
    -0.06
    ferences
    -0.06
    ÄŁan
    -0.06
    åļ
    -0.06
    ofire
    -0.06
    erial
    -0.06
    POSITIVE LOGITS
     recent
    0.12
    recent
    0.10
     recently
    0.09
     research
    0.07
     lately
    0.07
     Recently
    0.07
     Recent
    0.07
    /current
    0.07
     reports
    0.07
     evidence
    0.07
    Activations Density 0.011%

    No Known Activations