© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71074
    Prev
    Next
    INDEX
    Explanations

    numerical references and identifiers in a document

    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
    owan
    -0.06
    erson
    -0.06
    .VisualBasic
    -0.06
    wan
    -0.06
    agan
    -0.06
    ewn
    -0.06
     hus
    -0.06
    Ģìŀ¥
    -0.06
    020
    -0.06
    021
    -0.06
    POSITIVE LOGITS
    elib
    0.07
    .Hit
    0.07
    uento
    0.07
    ä¸ī个
    0.07
    ãİ
    0.07
     pages
    0.07
    enticator
    0.07
    pages
    0.06
    /pages
    0.06
    'gc
    0.06
    Activations Density 0.018%

    No Known Activations