© 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. 17-LLAMASCOPE-RES-131K
    6. 93438
    Prev
    Next
    INDEX
    Explanations

    references to Chinese government activities and its relations with foreign entities

    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
    æı
    -0.07
    etu
    -0.07
    olla
    -0.06
    åħ¥åı£
    -0.06
    linger
    -0.06
    entai
    -0.06
    vore
    -0.06
    aras
    -0.06
    encil
    -0.06
    anj
    -0.06
    POSITIVE LOGITS
     military
    0.07
     aggressive
    0.07
     Individuals
    0.07
     directly
    0.07
     Military
    0.06
    ког
    0.06
     ministries
    0.06
     entity
    0.06
     individuals
    0.06
     government
    0.06
    Activations Density 0.012%

    No Known Activations