© 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. 29347
    Prev
    Next
    INDEX
    Explanations

    terms related to civil society and social organizations

    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
    ãĥĥãĤ«ãĥ¼
    -0.07
    éĺ
    -0.07
    onen
    -0.07
    ximo
    -0.07
    acl
    -0.07
     režim
    -0.07
    gebn
    -0.07
    нед
    -0.07
     GetHashCode
    -0.07
    _ETH
    -0.07
    POSITIVE LOGITS
     organizations
    0.08
     sector
    0.08
     space
    0.08
     organisations
    0.07
     spaces
    0.07
     sectors
    0.07
     groups
    0.07
    ëĭ¨ì²´
    0.06
    kova
    0.06
     watchdog
    0.06
    Activations Density 0.002%

    No Known Activations