© 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. 117306
    Prev
    Next
    INDEX
    Explanations

    terms related to curling and its significance in Manitoba

    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
     Races
    -0.07
     Soccer
    -0.07
     racing
    -0.07
    Ð
    -0.07
     Frank
    -0.06
     races
    -0.06
    ancel
    -0.06
    avage
    -0.06
     soccer
    -0.06
    race
    -0.06
    POSITIVE LOGITS
     Curl
    0.09
     furnace
    0.07
     curl
    0.07
     Sniper
    0.07
    anean
    0.07
    idot
    0.07
     Furn
    0.07
     yarn
    0.07
     Team
    0.06
    .enterprise
    0.06
    Activations Density 0.002%

    No Known Activations