© 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. 60557
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, particularly those associated with access modifiers like public and private

    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
    osit
    -0.07
    linger
    -0.07
    amo
    -0.07
    uae
    -0.07
    ari
    -0.06
    act
    -0.06
    ayload
    -0.06
    ÑĢемÑı
    -0.06
    anske
    -0.06
     localVar
    -0.06
    POSITIVE LOGITS
    anners
    0.06
    /false
    0.06
    evice
    0.06
    jian
    0.06
    .EntityFramework
    0.06
    öh
    0.06
    Æ¡
    0.06
    à¥ĩà¤Ł
    0.06
     inf
    0.06
     wast
    0.06
    Activations Density 0.002%

    No Known Activations