© 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. 119470
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and critique in artistic 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
     accounts
    -0.06
     ãĤ°
    -0.06
    анÑĮ
    -0.06
    sworth
    -0.06
    accounts
    -0.06
    Compat
    -0.06
    kla
    -0.06
    èİİ
    -0.06
    osy
    -0.06
     articles
    -0.06
    POSITIVE LOGITS
     your
    0.07
    ä½łçļĦ
    0.07
    ucid
    0.07
    ugi
    0.07
    onal
    0.06
    -pad
    0.06
    ogue
    0.06
    isode
    0.06
    -notes
    0.06
    æĤ¨çļĦ
    0.06
    Activations Density 0.003%

    No Known Activations