© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89533
    Prev
    Next
    INDEX
    Explanations

    specific gaming mechanics and strategies

    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
    elman
    -0.07
    enville
    -0.07
    quate
    -0.06
    polator
    -0.06
    ήν
    -0.06
    ä¼´
    -0.06
    .Mutable
    -0.06
     earlier
    -0.06
    etically
    -0.06
     project
    -0.06
    POSITIVE LOGITS
     memor
    0.07
    ught
    0.07
     Strategy
    0.07
    observ
    0.06
    ãĤ´ãĥª
    0.06
    .learn
    0.06
    ÑĢож
    0.06
    /*č↵
    0.06
     USPS
    0.06
     strategy
    0.06
    Activations Density 0.002%

    No Known Activations