© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1481
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations related to equations

    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
    lut
    -0.07
    rede
    -0.06
    lay
    -0.06
    lide
    -0.06
    rm
    -0.06
    ÙĪÙĦد
    -0.06
     ado
    -0.06
    .kotlin
    -0.06
    abouts
    -0.06
    ynchronized
    -0.06
    POSITIVE LOGITS
    gether
    0.07
    anford
    0.07
    ácil
    0.07
    chandle
    0.06
    gamber
    0.06
    apgolly
    0.06
    ChangedEventArgs
    0.06
    etter
    0.06
    isans
    0.06
     Wade
    0.06
    Activations Density 0.007%

    No Known Activations