© 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. 29182
    Prev
    Next
    INDEX
    Explanations

    key terms related to autocratic leadership and governance

    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
    okit
    -0.07
     Sisters
    -0.07
     sisters
    -0.07
    azer
    -0.07
    estroy
    -0.07
    ilent
    -0.07
    ullan
    -0.07
     heroine
    -0.06
    297
    -0.06
     Ñĩим
    -0.06
    POSITIVE LOGITS
    iman
    0.08
    plements
    0.07
     absolut
    0.07
    à¤Ĥश
    0.07
     dyn
    0.07
     monarch
    0.07
     legitimacy
    0.06
    hos
    0.06
     power
    0.06
     legitim
    0.06
    Activations Density 0.013%

    No Known Activations