© 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. 89208
    Prev
    Next
    INDEX
    Explanations

    references to military command structures and accountability

    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
     Clerk
    -0.08
    alama
    -0.07
    nech
    -0.07
    vie
    -0.07
    .sun
    -0.07
    بÙĪاسطة
    -0.07
    ond
    -0.07
    ĥĿ
    -0.07
    upa
    -0.07
    AGENT
    -0.06
    POSITIVE LOGITS
     higher
    0.12
     senior
    0.10
    higher
    0.10
     Higher
    0.10
     highest
    0.10
    Higher
    0.08
     Senior
    0.08
     upper
    0.08
    highest
    0.08
     top
    0.07
    Activations Density 0.034%

    No Known Activations