© 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. 15-LLAMASCOPE-RES-131K
    6. 90523
    Prev
    Next
    INDEX
    Explanations

    mathematic and scientific notation within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Empty spaces or breaks between mathematical/technical expressions in scientific papers, often separating equations or marking transitions between technical content.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ocator
    -0.08
    ekil
    -0.08
    ternet
    -0.07
    benh
    -0.07
     arsch
    -0.07
    skirts
    -0.07
    teki
    -0.07
    nda
    -0.07
    /WebAPI
    -0.07
    teri
    -0.07
    POSITIVE LOGITS
     Dit
    0.07
    iang
    0.07
    ula
    0.06
    ans
    0.06
    asan
    0.06
    GAN
    0.05
    ol
    0.05
    al
    0.05
     dit
    0.05
     Caesar
    0.05
    Activations Density 0.098%

    No Known Activations