© 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. 60573
    Prev
    Next
    INDEX
    Explanations

    mentions of U.S. states and their abbreviations

    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
    گاÙĩ
    -0.06
    heels
    -0.06
    uela
    -0.06
    ypy
    -0.06
    lia
    -0.06
    asio
    -0.06
    oooooooo
    -0.06
    ogn
    -0.06
    -navbar
    -0.06
    ruc
    -0.06
    POSITIVE LOGITS
    amedi
    0.07
     Vend
    0.07
    HEMA
    0.06
     برد
    0.06
    ÙĪÛĮÛĮ
    0.06
     suppressed
    0.06
    inn
    0.06
    ео
    0.06
    ÙĪبÛĮ
    0.06
    (AP
    0.06
    Activations Density 0.008%

    No Known Activations