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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29659
    Prev
    Next
    INDEX
    Explanations

    terms related to betting odds and racing markets

    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
    liers
    -0.07
    itung
    -0.06
     bench
    -0.06
     Rent
    -0.06
    ulta
    -0.06
     Rental
    -0.06
    /Private
    -0.06
    atsu
    -0.06
     trump
    -0.06
    ields
    -0.06
    POSITIVE LOGITS
     odds
    0.10
     Odds
    0.09
    hap
    0.07
     likelihood
    0.07
    ombo
    0.06
    composite
    0.06
     assigning
    0.06
    ìĺĪ
    0.06
    likelihood
    0.06
     Composite
    0.06
    Activations Density 0.011%

    No Known Activations