© 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. 15-LLAMASCOPE-RES-131K
    11. 27471
    Prev
    Next
    INDEX
    Explanations

    themes related to survival and complex societal structures

    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
     ilet
    -0.07
    ãĥ¬ãĥ³
    -0.06
    ICODE
    -0.06
     paramMap
    -0.06
    chodu
    -0.06
    coe
    -0.06
     पà¤ķ
    -0.06
    wich
    -0.06
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.06
     é
    -0.06
    POSITIVE LOGITS
    RIX
    0.07
     Hayward
    0.07
    EDIA
    0.06
    oen
    0.06
    fried
    0.06
    PERT
    0.06
    anye
    0.06
     fatalError
    0.06
    crud
    0.06
    umo
    0.06
    Activations Density 0.010%

    No Known Activations