© 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. 15-LLAMASCOPE-RES-131K
    11. 395
    Prev
    Next
    INDEX
    Explanations

    numerical references and counts within 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
    bid
    -0.08
    imdi
    -0.07
    lash
    -0.06
    ields
    -0.06
    isk
    -0.06
    ÙĪاز
    -0.06
    ouz
    -0.06
    arat
    -0.06
    fra
    -0.06
    зи
    -0.06
    POSITIVE LOGITS
    esson
    0.07
    gle
    0.07
    |int
    0.07
    DITION
    0.06
    itele
    0.06
     Lange
    0.06
    PackageManager
    0.06
    icari
    0.06
     edition
    0.06
     Chronicle
    0.06
    Activations Density 0.026%

    No Known Activations