© 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. 60471
    Prev
    Next
    INDEX
    Explanations

    ticker symbols and stock market-related terms

    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
     Bracket
    -0.06
    unami
    -0.06
     Gabriel
    -0.06
     loop
    -0.06
     bracket
    -0.06
    portion
    -0.06
    ç«ĭãģ¦
    -0.05
    ismet
    -0.05
    оÑİз
    -0.05
    irling
    -0.05
    POSITIVE LOGITS
    atas
    0.07
    æłª
    0.07
    chas
    0.07
    uga
    0.07
    awai
    0.07
     shares
    0.07
    StackNavigator
    0.07
    æݧ
    0.07
     abyss
    0.07
    /share
    0.07
    Activations Density 0.004%

    No Known Activations