© 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 EvalsExportsinterp-engineNEWAPI 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. 70131
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or association

    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
    æĥħ
    -0.09
    大
    -0.07
    å°ı
    -0.07
    äºĭ
    -0.07
    å¿ĥ
    -0.07
    å°ı说
    -0.06
    æīĭ
    -0.06
    icens
    -0.06
    人
    -0.06
    pras
    -0.06
    POSITIVE LOGITS
    ardon
    0.07
     addCriterion
    0.07
    ếu
    0.07
    ãģĦãĤĭ
    0.07
     MouseButton
    0.06
    еÑģÑĤи
    0.06
    âķĿ
    0.06
    ÙħاÙĨÛĮ
    0.06
     FileInfo
    0.06
    AGMA
    0.06
    Activations Density 0.011%

    No Known Activations