© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 17302
    Prev
    Next
    INDEX
    Explanations

    programming keywords related to class and module inheritance in code

    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
    ifer
    -0.06
     Blond
    -0.06
    kul
    -0.05
     Intersection
    -0.05
    ÅĽnie
    -0.05
    ÙĪØ±Øª
    -0.05
    eto
    -0.05
    äng
    -0.05
    aptor
    -0.05
    ewan
    -0.05
    POSITIVE LOGITS
    sÃŃ
    0.07
    oucher
    0.07
     Alic
    0.07
    imes
    0.07
     chung
    0.07
    icÃŃ
    0.07
     è©ķ価
    0.07
     scrap
    0.07
    ongs
    0.07
    incer
    0.06
    Activations Density 0.001%

    No Known Activations