© 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. 54067
    Prev
    Next
    INDEX
    Explanations

    significant numerical references or indexes in text

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ju
    -0.07
    liqu
    -0.06
    mani
    -0.06
     credits
    -0.06
     malt
    -0.06
     briefing
    -0.06
    ÑĢей
    -0.06
    redo
    -0.06
     decode
    -0.06
    lier
    -0.06
    POSITIVE LOGITS
     Monad
    0.09
     Bakan
    0.08
    Tracker
    0.07
     Gret
    0.07
     circum
    0.07
     WAL
    0.07
     Elias
    0.06
    anche
    0.06
    TERS
    0.06
     CPR
    0.06
    Activations Density 0.002%

    No Known Activations