© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 86103
    Prev
    Next
    INDEX
    Explanations

    references to military operations and equipment

    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
    -INF
    -0.07
    OfWork
    -0.07
    ainers
    -0.07
    .getValueAt
    -0.07
    éł¼
    -0.07
    ilos
    -0.07
    iaux
    -0.07
    ibase
    -0.06
    fos
    -0.06
    ipers
    -0.06
    POSITIVE LOGITS
    erve
    0.06
     missions
    0.06
     purposes
    0.06
    igon
    0.06
     Agencies
    0.06
     duties
    0.06
     service
    0.06
    EMON
    0.06
     Barrier
    0.06
     Himal
    0.06
    Activations Density 0.066%

    No Known Activations