© 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. 56547
    Prev
    Next
    INDEX
    Explanations

    phrases indicating terms and conditions associated with prices and changes

    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
    ale
    -0.06
    ansi
    -0.06
    ys
    -0.06
     Spicer
    -0.06
    emit
    -0.06
    lette
    -0.06
     elevate
    -0.05
    ogl
    -0.05
    aria
    -0.05
     Cunningham
    -0.05
    POSITIVE LOGITS
     metab
    0.08
    cka
    0.07
    _CheckedChanged
    0.07
    fik
    0.07
    .metamodel
    0.07
    ceipt
    0.07
    .TestCase
    0.07
    utron
    0.07
     klu
    0.07
    Amazon
    0.06
    Activations Density 0.001%

    No Known Activations