© 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. 128139
    Prev
    Next
    INDEX
    Explanations

    references to official events and immigration policies

    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
    (æľĪ
    -0.07
    ynet
    -0.07
    ERP
    -0.07
     doPost
    -0.07
    letal
    -0.07
    ÑĢÑıдÑĥ
    -0.07
    ỳ
    -0.07
    483
    -0.07
     :č↵
    -0.07
    canf
    -0.07
    POSITIVE LOGITS
     etc
    0.08
    ãģªãģ©
    0.07
     ÑĤоÑīо
    0.06
    uru
    0.06
     tid
    0.06
    angan
    0.06
     plus
    0.06
     finally
    0.06
     ÙģÙĬÙĩا
    0.06
    news
    0.06
    Activations Density 0.039%

    No Known Activations