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

    Neuronpedia

    Jacobian LensNEW
    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. 56053
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "reason" and related concepts of purpose and justification

    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
    миÑĢ
    -0.07
    anka
    -0.07
    riel
    -0.06
    ESA
    -0.06
    çĶ¨çļĦ
    -0.06
    iller
    -0.06
    ikan
    -0.06
     erk
    -0.06
    vit
    -0.06
    jet
    -0.06
    POSITIVE LOGITS
     alone
    0.09
    alone
    0.09
    ä¹ĭä¸Ģ
    0.09
    among
    0.07
    annes
    0.07
     sake
    0.07
     ÙĪغÙĬر
    0.07
    NAL
    0.07
     among
    0.07
    nement
    0.07
    Activations Density 0.003%

    No Known Activations