© 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. 70741
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries throughout the text

    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
    ัà¸Ļย
    -0.08
    èĿ
    -0.07
     кÑĢем
    -0.07
    oria
    -0.06
    ansa
    -0.06
    ož
    -0.06
    ieux
    -0.06
    orgia
    -0.06
    aily
    -0.06
    ói
    -0.06
    POSITIVE LOGITS
     then
    0.08
     entonces
    0.08
    Then
    0.08
     Then
    0.08
    then
    0.08
    	then
    0.07
     chances
    0.07
    atrice
    0.07
     li
    0.07
    elman
    0.07
    Activations Density 0.013%

    No Known Activations