© 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. 9-LLAMASCOPE-RES-131K
    11. 96362
    Prev
    Next
    INDEX
    Explanations

    programming language elements, specifically those related to structure and organization 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
    rov
    -0.07
    uji
    -0.07
    apia
    -0.07
    ãĤ
    -0.07
    ateria
    -0.07
    azzi
    -0.07
    lan
    -0.07
    rait
    -0.06
    itu
    -0.06
    .updateDynamic
    -0.06
    POSITIVE LOGITS
     Grace
    0.07
     abs
    0.06
    ople
    0.06
    Grace
    0.06
    ascar
    0.06
    ác
    0.06
    ibern
    0.06
    EDA
    0.06
     cum
    0.05
    ikler
    0.05
    Activations Density 0.001%

    No Known Activations