© 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. 70795
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or association with entities

    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
     Amerik
    -0.06
    erator
    -0.06
    .dy
    -0.06
    æĿ¥èĩª
    -0.06
    obe
    -0.06
    ara
    -0.06
     Kou
    -0.06
     ÑĥкÑĢаÑĹнÑģÑĮкоÑĹ
    -0.06
    /tree
    -0.06
    erate
    -0.06
    POSITIVE LOGITS
     national
    0.10
     economy
    0.09
     nation
    0.09
     nationals
    0.09
     National
    0.09
     country
    0.08
     government
    0.07
    National
    0.07
    -US
    0.07
     state
    0.07
    Activations Density 0.041%

    No Known Activations