© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5716
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to equations and variables

    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
    ardin
    -0.07
    lander
    -0.07
    mdl
    -0.07
    éĻ
    -0.07
    à¸Ńà¸ļ
    -0.06
    onder
    -0.06
    μοÏģ
    -0.06
     cul
    -0.06
    LOB
    -0.06
    alar
    -0.06
    POSITIVE LOGITS
    uds
    0.07
    nodeValue
    0.06
    unce
    0.06
    xea
    0.06
    lights
    0.06
    rous
    0.06
    asco
    0.06
    ìĿ´íĬ¸
    0.06
    inea
    0.06
    nown
    0.06
    Activations Density 0.165%

    No Known Activations