© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 58113
    Prev
    Next
    INDEX
    Explanations

    comparative phrases typically involving "of" and "than."

    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
    ÏĢά
    -0.08
    Orm
    -0.08
    antwort
    -0.08
     ÑĤакже
    -0.08
    ERCHANT
    -0.08
    ãİ
    -0.07
     ayrıca
    -0.07
    wd
    -0.07
     ëĺIJíķľ
    -0.07
     chứ
    -0.07
    POSITIVE LOGITS
     being
    0.11
     necessarily
    0.10
     having
    0.10
     just
    0.10
     merely
    0.09
    being
    0.08
     ones
    0.08
     usual
    0.08
     simply
    0.07
     اÛĮÙĨÚ©Ùĩ
    0.07
    Activations Density 0.017%

    No Known Activations