© 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 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. 29344
    Prev
    Next
    INDEX
    Explanations

    references to health-conscious beverage options

    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
    .nd
    -0.06
    .gov
    -0.06
     gente
    -0.06
    stu
    -0.06
     jealous
    -0.06
     rol
    -0.06
    aravel
    -0.05
    icari
    -0.05
    Fault
    -0.05
     fault
    -0.05
    POSITIVE LOGITS
    ski
    0.07
    sal
    0.07
    ataka
    0.07
    oplast
    0.07
    illes
    0.07
    Å¡et
    0.07
    macro
    0.06
    _TestCase
    0.06
    kok
    0.06
    cke
    0.06
    Activations Density 0.016%

    No Known Activations