© 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. 15-LLAMASCOPE-RES-131K
    11. 88422
    Prev
    Next
    INDEX
    Explanations

    key terms related to conflict and tension in political contexts

    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
    ÙĪØ·
    -0.07
    celik
    -0.06
     schö
    -0.06
    frauen
    -0.06
    acket
    -0.06
    æľĢåĪĿ
    -0.06
     WARRANT
    -0.06
     schön
    -0.06
     iParam
    -0.06
    cai
    -0.06
    POSITIVE LOGITS
     already
    0.09
     upcoming
    0.08
    already
    0.07
    aver
    0.07
     recently
    0.07
     pending
    0.07
    ableView
    0.07
     ongoing
    0.07
     Already
    0.07
     Ñĥже
    0.06
    Activations Density 0.024%

    No Known Activations