© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 54494
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols related to equations and functions

    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
    relude
    -0.07
    ÑĥÑĢи
    -0.06
    antal
    -0.06
    erson
    -0.06
    лаÑĪ
    -0.06
    bris
    -0.06
    ossible
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    eração
    -0.06
    ÙĪØ¯Ùĩ
    -0.06
    POSITIVE LOGITS
    Ĺi
    0.07
    iban
    0.06
    eny
    0.06
    ìĭ
    0.06
    ालà¤ķ
    0.06
    olleyError
    0.06
    صاÙĦ
    0.06
    žit
    0.06
    wers
    0.06
    омеÑĢ
    0.06
    Activations Density 0.137%

    No Known Activations