© 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. 14182
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data analysis and modeling

    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
     Abstract
    -0.07
    é¼
    -0.06
    orce
    -0.06
     fos
    -0.06
    .sul
    -0.06
     currents
    -0.06
     abstraction
    -0.06
    Abstract
    -0.06
    abstract
    -0.06
     suy
    -0.06
    POSITIVE LOGITS
     suspended
    0.07
    ãi
    0.07
     fines
    0.07
     suspension
    0.06
     snow
    0.06
     sticking
    0.06
     fil
    0.06
    Å¡ku
    0.06
     stick
    0.06
    WidgetItem
    0.06
    Activations Density 0.026%

    No Known Activations