© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119705
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical notations and symbols

    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
     kidd
    -0.06
     Naw
    -0.06
    oor
    -0.06
    ett
    -0.06
    ederland
    -0.06
     Blackburn
    -0.06
    stat
    -0.06
    repid
    -0.06
    aja
    -0.06
    .intValue
    -0.06
    POSITIVE LOGITS
     alike
    0.08
    encers
    0.07
    aversable
    0.07
    ÑĤиÑĢов
    0.07
    corev
    0.07
    .minecraftforge
    0.07
    ispens
    0.07
    ëijĺ
    0.07
    tant
    0.06
    دÛĮگر
    0.06
    Activations Density 0.171%

    No Known Activations