© 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. 61400
    Prev
    Next
    INDEX
    Explanations

    references to military involvement and contributions, especially from diverse groups during wartime

    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
    -0.07
     Missile
    -0.06
    aban
    -0.06
    TERN
    -0.06
    erte
    -0.06
     Booking
    -0.06
    impan
    -0.06
    ãĤ¿ãĥ³
    -0.06
    пп
    -0.06
    marvin
    -0.06
    POSITIVE LOGITS
     contributions
    0.07
     fought
    0.07
     contribution
    0.07
    ç·Ĵ
    0.06
     attachments
    0.06
     Fighting
    0.06
     formations
    0.06
     participation
    0.06
     Masc
    0.06
     fighting
    0.06
    Activations Density 0.032%

    No Known Activations