© 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. 107318
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate research and discoveries made by academic or scientific teams

    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
    AccessException
    -0.07
    urus
    -0.06
    ovie
    -0.06
    оваÑĢ
    -0.06
    ettes
    -0.06
    allon
    -0.06
    322
    -0.06
    uC
    -0.06
    acco
    -0.05
    CTYPE
    -0.05
    POSITIVE LOGITS
    oleÄį
    0.07
     successfully
    0.07
    oftware
    0.07
    Ðĭ
    0.07
    aya
    0.06
     study
    0.06
    ê³
    0.06
     proposal
    0.06
     Kare
    0.06
     successful
    0.06
    Activations Density 0.020%

    No Known Activations