© 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. 9-LLAMASCOPE-RES-131K
    11. 95392
    Prev
    Next
    INDEX
    Explanations

    adverbs and phrases indicating frequency 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
    ÙĪص
    -0.07
    Recommended
    -0.07
    inea
    -0.07
    iolet
    -0.07
    osal
    -0.07
    atrix
    -0.06
    ostel
    -0.06
    ObjectContext
    -0.06
    richt
    -0.06
    NODE
    -0.06
    POSITIVE LOGITS
     to
    0.06
     Suites
    0.06
    .observable
    0.05
     olsa
    0.05
     into
    0.05
    ë£Į
    0.05
    toFloat
    0.05
    úsqueda
    0.05
    ê³ł
    0.05
    ORITY
    0.05
    Activations Density 0.050%

    No Known Activations