© 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. 543
    Prev
    Next
    INDEX
    Explanations

    parentheses and parentheses-related structures in programming 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
    ÑĸлÑĸ
    -0.06
    omain
    -0.06
    lings
    -0.06
    .learn
    -0.06
    ɵ
    -0.06
    ообÑĢаз
    -0.06
     تÙĥÙĬÙĬÙģ
    -0.06
    à¹ģà¸Ĥ
    -0.06
    stitial
    -0.06
     Sunrise
    -0.06
    POSITIVE LOGITS
    rello
    0.07
     Rencontres
    0.06
    .openConnection
    0.06
    pez
    0.06
    çĪ½
    0.06
    ivi
    0.06
    ä¼
    0.06
     frau
    0.06
    aspers
    0.06
    ê¹
    0.06
    Activations Density 0.001%

    No Known Activations