© 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. 15-LLAMASCOPE-RES-131K
    11. 27078
    Prev
    Next
    INDEX
    Explanations

    phrases related to betting odds and predictions 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
    ajar
    -0.06
     Loose
    -0.06
    ournal
    -0.06
     locator
    -0.06
     Locator
    -0.06
    olo
    -0.06
    á»Ĺ
    -0.05
    olk
    -0.05
    ä¿Ŀ
    -0.05
     pursued
    -0.05
    POSITIVE LOGITS
     prediction
    0.07
     å¯
    0.07
    Äįer
    0.07
    zos
    0.07
    gba
    0.07
    Streamer
    0.07
    å¯Ħ
    0.07
     predictions
    0.07
    opp
    0.07
    preg
    0.07
    Activations Density 0.003%

    No Known Activations