© 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. 107328
    Prev
    Next
    INDEX
    Explanations

    numerical values and associated terms in the context of sports statistics or scores

    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
    UnderTest
    -0.08
    wig
    -0.07
    MLS
    -0.07
    utsch
    -0.07
    quo
    -0.07
    InParameter
    -0.07
    ignite
    -0.07
    волÑı
    -0.07
    ForResult
    -0.07
    SupportedContent
    -0.07
    POSITIVE LOGITS
    ieri
    0.06
    ovel
    0.06
     near
    0.06
    variant
    0.05
    jad
    0.05
    amba
    0.05
     Honest
    0.05
     consecutive
    0.05
    enance
    0.05
    098
    0.05
    Activations Density 0.009%

    No Known Activations