© 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. 76101
    Prev
    Next
    INDEX
    Explanations

    terms related to airline services and destinations

    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
    StackTrace
    -0.06
    ολ
    -0.06
    .delivery
    -0.06
    wat
    -0.06
     Federation
    -0.06
    çuk
    -0.06
    /topics
    -0.06
    ानत
    -0.06
     stadiums
    -0.06
    mise
    -0.06
    POSITIVE LOGITS
     Ryan
    0.07
    uns
    0.07
    ÄĽt
    0.06
    ler
    0.06
     terminal
    0.06
    kiem
    0.06
    Ryan
    0.06
    imulator
    0.06
    íݸ
    0.06
     foreign
    0.06
    Activations Density 0.013%

    No Known Activations