© 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. 71057
    Prev
    Next
    INDEX
    Explanations

    negative attributes and consequences related to coffee and system performance

    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
    600
    -0.06
    jong
    -0.06
     Filed
    -0.06
    iles
    -0.06
     prevailing
    -0.06
    ãģıãĤĮãģŁ
    -0.06
     Greg
    -0.06
    dh
    -0.05
     pig
    -0.05
     mount
    -0.05
    POSITIVE LOGITS
    itori
    0.07
    sko
    0.07
    AffineTransform
    0.07
    sÃŃ
    0.07
    abase
    0.07
    à¤łà¤¨
    0.07
     âķ
    0.07
    porto
    0.07
    едак
    0.07
     \/
    0.07
    Activations Density 0.001%

    No Known Activations