© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104979
    Prev
    Next
    INDEX
    Explanations

    import statements and the structure of a React application

    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
    ÑĢиÑĩ
    -0.07
    chg
    -0.07
    .synthetic
    -0.07
     onDataChange
    -0.07
    CodeAt
    -0.07
    edith
    -0.06
    DAC
    -0.06
    irm
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    .Arguments
    -0.06
    POSITIVE LOGITS
    meni
    0.07
    ServiceProvider
    0.07
    RootElement
    0.07
     factory
    0.06
     prov
    0.06
    .forRoot
    0.06
    inden
    0.06
    .LoggerFactory
    0.06
    ConverterFactory
    0.06
     MaterialApp
    0.06
    Activations Density 0.055%

    No Known Activations