© 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. 62312
    Prev
    Next
    INDEX
    Explanations

    instances of team records and performance metrics in sports contexts

    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
    олом
    -0.07
    .scalablytyped
    -0.07
    Metrics
    -0.07
    Hub
    -0.07
    cies
    -0.07
    оба
    -0.06
     æ½
    -0.06
    announce
    -0.06
    .TODO
    -0.06
     Hub
    -0.06
    POSITIVE LOGITS
    vertising
    0.06
    AZY
    0.06
     Sar
    0.06
    poi
    0.06
    orie
    0.06
    ibi
    0.06
    let
    0.06
    ilion
    0.06
    orph
    0.06
    egin
    0.05
    Activations Density 0.002%

    No Known Activations