© 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. 128464
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software testing and performance metrics

    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
    été
    -0.06
    apy
    -0.06
     cop
    -0.06
    Å¡ak
    -0.06
    throp
    -0.06
    ongan
    -0.05
    432
    -0.05
    ERSIST
    -0.05
     Zub
    -0.05
     pet
    -0.05
    POSITIVE LOGITS
    .testng
    0.08
     Test
    0.08
     Reporting
    0.07
    Recording
    0.07
    Reporter
    0.07
    /report
    0.07
    TestId
    0.07
    /Test
    0.07
     reporting
    0.07
    ieux
    0.07
    Activations Density 0.037%

    No Known Activations