© 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. 60353
    Prev
    Next
    INDEX
    Explanations

    mentions of names and associated statistics in a sports context

    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
     Arena
    -0.06
     Lens
    -0.06
     Fitzgerald
    -0.06
    ethe
    -0.06
     Bil
    -0.05
     Sanctuary
    -0.05
     Banner
    -0.05
     Gael
    -0.05
    Integral
    -0.05
     cred
    -0.05
    POSITIVE LOGITS
    еÑĢин
    0.08
    ereum
    0.08
     Tigers
    0.08
    á»ĩu
    0.08
     pitcher
    0.08
     Dodgers
    0.08
     pitching
    0.07
    uco
    0.07
    Pitch
    0.07
    pitch
    0.07
    Activations Density 0.112%

    No Known Activations