© 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. 60345
    Prev
    Next
    INDEX
    Explanations

    occurrences of definite articles

    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
    INET
    -0.07
    avad
    -0.07
    allback
    -0.07
    achu
    -0.07
    adele
    -0.07
    hte
    -0.06
    ypes
    -0.06
    ont
    -0.06
     Morrow
    -0.06
    mare
    -0.06
    POSITIVE LOGITS
    Ñİк
    0.07
    ردÙĩ
    0.06
     burdens
    0.06
     resultant
    0.06
     premise
    0.06
     thumbs
    0.06
    ÏģοÏħ
    0.06
     story
    0.06
    china
    0.06
    Äįer
    0.06
    Activations Density 0.019%

    No Known Activations