© 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. 9-LLAMASCOPE-RES-131K
    11. 99112
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values, particularly related to years and quantities

    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
    edir
    -0.07
     iParam
    -0.07
    odesk
    -0.07
    ÑĻ
    -0.07
    URA
    -0.07
    assel
    -0.07
    alles
    -0.07
    øy
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    ocoder
    -0.07
    POSITIVE LOGITS
    sembl
    0.07
     aforementioned
    0.07
    chor
    0.06
    legate
    0.06
    ergy
    0.06
    otton
    0.05
    ανδ
    0.05
    caff
    0.05
    óst
    0.05
     ans
    0.05
    Activations Density 0.013%

    No Known Activations