© 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. 54912
    Prev
    Next
    INDEX
    Explanations

    key moments in a sporting event

    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
    .jquery
    -0.07
    ÙĪزÛĮ
    -0.07
    .oper
    -0.07
    олом
    -0.07
    atform
    -0.07
    defs
    -0.07
    èİ«
    -0.07
     Annunci
    -0.07
    ınızda
    -0.07
    तम
    -0.07
    POSITIVE LOGITS
     pitching
    0.08
     goalt
    0.07
    undi
    0.07
    iasi
    0.07
     goalie
    0.07
     goalkeeper
    0.07
     quarterback
    0.07
     Consolid
    0.06
    aign
    0.06
     pitchers
    0.06
    Activations Density 0.041%

    No Known Activations