© 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. 15-LLAMASCOPE-RES-131K
    6. 90612
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and transitional phrases in a text

    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
    بÙĪØ±
    -0.06
     lately
    -0.06
    377
    -0.06
    λÏħ
    -0.06
     rub
    -0.06
     over
    -0.06
    BOTTOM
    -0.06
    İ
    -0.06
    erif
    -0.05
    ithe
    -0.05
    POSITIVE LOGITS
    /post
    0.07
    edn
    0.07
    .scalablytyped
    0.07
    EATURE
    0.07
    ondheim
    0.07
     Robbins
    0.07
    enville
    0.06
     ÙħÛĮÙĦادÛĮ
    0.06
    owel
    0.06
    .Cmd
    0.06
    Activations Density 0.064%

    No Known Activations