© 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. 82285
    Prev
    Next
    INDEX
    Explanations

    references to military or defense-related entities and actions

    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
     اÙĦرÙħزÙĬØ©
    -0.06
    Ø´ÙĪد
    -0.06
    roit
    -0.06
     Yug
    -0.06
    atoi
    -0.06
    ige
    -0.06
     Abdullah
    -0.06
     prohib
    -0.06
    ctica
    -0.06
    aisal
    -0.06
    POSITIVE LOGITS
     Iranian
    0.16
     Iran
    0.15
     Tehran
    0.15
     Iranians
    0.15
    Iran
    0.14
     Persian
    0.13
    .ir
    0.11
     Ä°ran
    0.11
     Indiana
    0.11
     Pars
    0.11
    Activations Density 0.241%

    No Known Activations