© 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. 79651
    Prev
    Next
    INDEX
    Explanations

    statistical terms and concepts related to uncertainty and confidence intervals

    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
    âĻª
    -0.08
    ìĭĿìĿĦ
    -0.07
     Subtract
    -0.07
    .messaging
    -0.07
    aturas
    -0.07
    _GAP
    -0.07
    IBUTE
    -0.07
     multiplic
    -0.07
    enburg
    -0.07
     ******************************************************************************/↵
    -0.07
    POSITIVE LOGITS
     percentile
    0.12
     tail
    0.09
     tails
    0.08
    Tail
    0.08
    tail
    0.08
     extreme
    0.08
     Tail
    0.08
     median
    0.07
    95
    0.07
     upper
    0.07
    Activations Density 0.084%

    No Known Activations