© 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. 75890
    Prev
    Next
    INDEX
    Explanations

    references to wars throughout history

    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
    éģŃ
    -0.06
    _ctr
    -0.06
     suscept
    -0.06
    arrants
    -0.06
    breadcrumbs
    -0.06
    说è¯Ŀ
    -0.06
     intact
    -0.06
    ople
    -0.06
     jÃŃ
    -0.06
    OPLE
    -0.06
    POSITIVE LOGITS
     fought
    0.08
     waged
    0.08
     war
    0.07
    Clause
    0.07
    ucene
    0.07
     toll
    0.07
     conducted
    0.06
    aná
    0.06
    cio
    0.06
    decltype
    0.06
    Activations Density 0.044%

    No Known Activations