© 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. 73155
    Prev
    Next
    INDEX
    Explanations

    significant statistics and performance indicators in sports narratives

    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
     authDomain
    -0.07
    Legacy
    -0.07
    'gc
    -0.06
    BaseContext
    -0.06
     desar
    -0.06
    é³
    -0.06
    _Tis
    -0.06
     Cork
    -0.06
    /******/
    -0.06
    umsuz
    -0.06
    POSITIVE LOGITS
    indow
    0.07
    adil
    0.07
    WithError
    0.07
    enders
    0.07
    onom
    0.06
     Rowe
    0.06
    strup
    0.06
    endor
    0.06
    ModelProperty
    0.06
     edil
    0.06
    Activations Density 0.001%

    No Known Activations