© 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. 128894
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts, particularly those related to equations, functions, and inequalities

    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
    ÛĮدا
    -0.08
    quivo
    -0.07
    або
    -0.07
    Äįas
    -0.07
    adele
    -0.07
    ä¸įäºĨ
    -0.07
    fov
    -0.06
    iÄįky
    -0.06
    253
    -0.06
     залеж
    -0.06
    POSITIVE LOGITS
     surely
    0.07
    unch
    0.06
    anks
    0.06
     Bian
    0.06
    urst
    0.06
     only
    0.06
     being
    0.05
     bore
    0.05
    olt
    0.05
    æ¯ķ
    0.05
    Activations Density 0.112%

    No Known Activations