© 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. 15-LLAMASCOPE-RES-131K
    11. 85992
    Prev
    Next
    INDEX
    Explanations

    issues related to regulatory matters and workplace dissatisfaction

    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
    лÑİб
    -0.08
    BorderStyle
    -0.08
    NST
    -0.07
    loff
    -0.07
    ẩm
    -0.07
    à¥įपर
    -0.07
    erox
    -0.07
    ÑĢеÑģÑĤ
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    ÑĤÑĢо
    -0.07
    POSITIVE LOGITS
     unspecified
    0.07
    herits
    0.06
     other
    0.06
    other
    0.06
     Hum
    0.06
     Dew
    0.06
    ictionaries
    0.06
     followed
    0.06
    -other
    0.06
     general
    0.06
    Activations Density 0.010%

    No Known Activations