© 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. 17-LLAMASCOPE-RES-131K
    11. 16982
    Prev
    Next
    INDEX
    Explanations

    financial terms related to salary cap management in sports

    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
    esome
    -0.08
    steller
    -0.07
    _mD
    -0.07
    pecified
    -0.07
    yme
    -0.07
    .capture
    -0.07
    -BEGIN
    -0.07
    uhan
    -0.07
    abee
    -0.07
    ekim
    -0.07
    POSITIVE LOGITS
     budget
    0.07
     Spot
    0.07
     constraint
    0.06
    urb
    0.06
     max
    0.06
     Budget
    0.06
     spot
    0.06
    rum
    0.06
     spending
    0.06
     payroll
    0.06
    Activations Density 0.011%

    No Known Activations