© 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. 106586
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to set theory and functional analysis

    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
    avana
    -0.07
     portion
    -0.06
    nano
    -0.06
    hip
    -0.06
    ’ÑıÑĤ
    -0.06
    ample
    -0.06
    odore
    -0.06
    raž
    -0.06
    ãĥ³ãĤ°
    -0.06
    byss
    -0.06
    POSITIVE LOGITS
    otty
    0.07
    emouth
    0.07
    readystatechange
    0.07
    235
    0.07
    \base
    0.06
    инов
    0.06
    ÏĦηÏĤ
    0.06
    thy
    0.06
    yyyyMMdd
    0.06
    ŀæĢ§
    0.06
    Activations Density 0.440%

    No Known Activations