© 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. 85092
    Prev
    Next
    INDEX
    Explanations

    phrases related to organization and categorization

    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
     詳細
    -0.06
    ÙĦÙĬÙĩ
    -0.06
    Han
    -0.06
     Twins
    -0.05
    unda
    -0.05
    енÑĮÑİ
    -0.05
    ادات
    -0.05
     quant
    -0.05
     kale
    -0.05
    lee
    -0.05
    POSITIVE LOGITS
     categories
    0.10
    categories
    0.09
     Categories
    0.07
    -categories
    0.07
     ëħĦëıĦë³Ħ
    0.07
    Categories
    0.07
    /category
    0.07
    _categories
    0.07
    ATEGORY
    0.07
     Category
    0.07
    Activations Density 0.013%

    No Known Activations