© 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. 15-LLAMASCOPE-RES-131K
    11. 104372
    Prev
    Next
    INDEX
    Explanations

    names of basketball players and their associated statistics

    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
    orthy
    -0.07
    ÃĹ↵↵
    -0.06
    ieu
    -0.06
    aju
    -0.06
    ItemCount
    -0.06
    elop
    -0.06
    ì
    -0.06
     ì§Ī
    -0.06
     Blond
    -0.06
     Nej
    -0.06
    POSITIVE LOGITS
    ample
    0.07
    iyas
    0.06
     Snowden
    0.06
     Bailey
    0.06
    iteDatabase
    0.06
    ardım
    0.06
    lis
    0.06
    cha
    0.06
    ISIS
    0.06
    /frontend
    0.06
    Activations Density 0.034%

    No Known Activations