© 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. 41112
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions, particularly the word "and."

    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
    ÌĨ
    -0.08
    meer
    -0.07
    quan
    -0.07
    ","",
    -0.07
    ãģħ
    -0.06
    âĢ¦↵↵↵
    -0.06
    peare
    -0.06
    .obtain
    -0.06
    engin
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
     ones
    0.14
     those
    0.11
    those
    0.10
     others
    0.09
     Ones
    0.09
     versus
    0.09
     Those
    0.08
     ê·¸ëłĩ
    0.08
    Those
    0.08
     ceux
    0.07
    Activations Density 0.013%

    No Known Activations