© 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. 58028
    Prev
    Next
    INDEX
    Explanations

    concepts related to international relations and diplomatic practices

    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
    ITTE
    -0.08
    们
    -0.08
     nét
    -0.07
    uchen
    -0.07
    rana
    -0.07
    ÅĤug
    -0.07
    ISCO
    -0.07
    IPH
    -0.07
    Suppress
    -0.07
    .openConnection
    -0.06
    POSITIVE LOGITS
     principle
    0.10
     doctrine
    0.08
     theory
    0.07
    apon
    0.07
     concept
    0.07
     Principle
    0.07
     principles
    0.07
    ism
    0.07
    ality
    0.07
    ivism
    0.06
    Activations Density 0.047%

    No Known Activations