© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27609
    Prev
    Next
    INDEX
    Explanations

    references to specific sports teams and leagues

    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
    uilt
    -0.07
    tc
    -0.06
    datatable
    -0.06
    isko
    -0.06
    èĥ¡
    -0.06
     Cros
    -0.06
    addock
    -0.06
    atives
    -0.06
    zzo
    -0.06
    anik
    -0.06
    POSITIVE LOGITS
    level
    0.07
    344
    0.07
     düzey
    0.07
    LOPT
    0.07
    ona
    0.07
     Rif
    0.07
     HomeController
    0.06
    onal
    0.06
    -level
    0.06
    oplevel
    0.06
    Activations Density 0.004%

    No Known Activations