© 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. 94289
    Prev
    Next
    INDEX
    Explanations

    details related to cricket matches and players' performances

    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
    itten
    -0.07
    ÑģÑĤи
    -0.07
    itize
    -0.06
    wu
    -0.06
    VISIBLE
    -0.06
    Reusable
    -0.06
    isable
    -0.06
    áh
    -0.06
    enler
    -0.06
    á»ĵng
    -0.06
    POSITIVE LOGITS
     cricket
    0.12
     Cricket
    0.11
     innings
    0.08
     batting
    0.08
     Test
    0.08
     Seam
    0.08
     bats
    0.08
     bowling
    0.08
     Pant
    0.08
     selectors
    0.07
    Activations Density 0.102%

    No Known Activations