© 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. 40939
    Prev
    Next
    INDEX
    Explanations

    gambling-related terms and statistics 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
    swift
    -0.07
    BootApplication
    -0.07
    kuk
    -0.07
    priv
    -0.07
    onda
    -0.07
    iaz
    -0.07
    -alist
    -0.07
    BOVE
    -0.06
    LEGRO
    -0.06
    çķª
    -0.06
    POSITIVE LOGITS
    unnel
    0.06
     odd
    0.06
     Odd
    0.06
    Odd
    0.06
    866
    0.06
     bet
    0.06
    ãģ©ãģĨ
    0.06
    288
    0.06
    äºĪ
    0.06
    888
    0.05
    Activations Density 0.006%

    No Known Activations