© 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. 106130
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in various contexts

    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
    hint
    -0.06
     caps
    -0.06
     accom
    -0.06
     rede
    -0.06
     ways
    -0.06
     suas
    -0.05
     rhet
    -0.05
     saja
    -0.05
     chance
    -0.05
    im
    -0.05
    POSITIVE LOGITS
    ï¼īãģ¯
    0.09
    人ãģ¯
    0.09
    andel
    0.09
    åŃIJãģ¯
    0.09
    andalone
    0.08
     ìĤ¬ëŀĮìĿĢ
    0.08
    è¿Ļç§į
    0.08
     nÃły
    0.08
    ISTR
    0.07
     latter
    0.07
    Activations Density 0.095%

    No Known Activations