© 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. 86718
    Prev
    Next
    INDEX
    Explanations

    date-related information, particularly focusing on significant events like births and deaths across various years

    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
     st
    -0.05
    oup
    -0.05
    âĢ¦↵
    -0.05
     “
    -0.05
     vener
    -0.05
     searchable
    -0.05
    _LIB
    -0.05
     Sawyer
    -0.05
    ener
    -0.05
    ior
    -0.05
    POSITIVE LOGITS
    LineStyle
    0.09
    ADDE
    0.09
    #End
    0.08
    _Method
    0.08
    PixelFormat
    0.08
    Ø¢Ùħ
    0.08
    .osgi
    0.08
    paque
    0.08
     EÅŁ
    0.08
    KHTML
    0.08
    Activations Density 0.000%

    No Known Activations