© 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. 125093
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, often related to individuals or entities in a particular context

    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
    andex
    -0.08
    ein
    -0.07
    otate
    -0.07
    perse
    -0.07
    inesis
    -0.07
    antee
    -0.07
    icaret
    -0.07
    ennon
    -0.07
    ÅŁehir
    -0.07
    antity
    -0.07
    POSITIVE LOGITS
     kn
    0.08
     Kn
    0.07
    kn
    0.07
    mare
    0.06
     shar
    0.06
     tor
    0.06
    egt
    0.06
    ripple
    0.06
     Erik
    0.06
     khá»ķ
    0.06
    Activations Density 0.018%

    No Known Activations