© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2198
    Prev
    Next
    INDEX
    Explanations

    JavaScript-related content and error handling scripts

    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
    abar
    -0.09
    oftware
    -0.08
    son
    -0.08
    кав
    -0.07
    ity
    -0.07
    sonian
    -0.07
    ulong
    -0.07
    oft
    -0.07
    endregion
    -0.07
    ansen
    -0.07
    POSITIVE LOGITS
    orman
    0.06
    661
    0.06
    iale
    0.06
     пеÑĩ
    0.06
    íĸ¥
    0.06
    人åĵ¡
    0.05
     ÙģÙĩرست
    0.05
    shade
    0.05
     Sector
    0.05
     sector
    0.05
    Activations Density 0.000%

    No Known Activations