© 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. 82261
    Prev
    Next
    INDEX
    Explanations

    punctuations and words indicating transitions or emphasis

    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
    aukee
    -0.07
    ÃŃg
    -0.07
    _callable
    -0.07
    ÑĦиÑĨи
    -0.06
    éĥ
    -0.06
    ecret
    -0.06
    tearDown
    -0.06
     BindingFlags
    -0.06
     FactoryGirl
    -0.06
    ripple
    -0.06
    POSITIVE LOGITS
     weather
    0.14
    weather
    0.12
     Weather
    0.12
    /weather
    0.12
    Weather
    0.10
     meteor
    0.10
    .weather
    0.10
     forecasts
    0.09
     forecast
    0.09
     forecasting
    0.09
    Activations Density 0.001%

    No Known Activations