© 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. 15-LLAMASCOPE-RES-131K
    11. 104327
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks and test-related functions or components

    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
    udeau
    -0.08
    ikh
    -0.06
    arus
    -0.06
    zet
    -0.06
    ools
    -0.06
    excel
    -0.06
     Foo
    -0.06
    alis
    -0.05
    _reverse
    -0.05
    reet
    -0.05
    POSITIVE LOGITS
    EDIA
    0.08
    _framework
    0.07
    \TestCase
    0.07
    rido
    0.07
    ä¸ĢåĮº
    0.07
     nghiá»ĩm
    0.06
    çŃĨ
    0.06
    .setUp
    0.06
    arness
    0.06
    iest
    0.06
    Activations Density 0.003%

    No Known Activations