© 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. 86863
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly focusing on code structure and function calls

    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
    orm
    -0.06
    ListOf
    -0.06
     Pac
    -0.06
    -ÑĤо
    -0.06
     Duke
    -0.06
     prim
    -0.06
    _apps
    -0.05
     Spicer
    -0.05
    anh
    -0.05
     slack
    -0.05
    POSITIVE LOGITS
    ettel
    0.08
    æĽ
    0.07
    kke
    0.07
    uned
    0.07
    çĮ
    0.07
    emann
    0.07
     pushViewController
    0.07
    ayne
    0.07
    unes
    0.06
    cheon
    0.06
    Activations Density 0.003%

    No Known Activations