© 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. 76005
    Prev
    Next
    INDEX
    Explanations

    terminology related to technology and sensors

    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
    .Messaging
    -0.07
     steering
    -0.07
    athi
    -0.06
    è³Ģ
    -0.06
     Overnight
    -0.06
     antioxid
    -0.06
    ountain
    -0.06
    nuts
    -0.06
    erville
    -0.06
     Arcade
    -0.06
    POSITIVE LOGITS
    READING
    0.07
     rugged
    0.07
     mains
    0.07
     yazılı
    0.07
     Field
    0.07
     ÄIJo
    0.07
    atee
    0.07
    ëŀĺ
    0.07
    ÙĬÙĩ
    0.06
    ırak
    0.06
    Activations Density 0.009%

    No Known Activations