© 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. 17-LLAMASCOPE-RES-131K
    11. 39956
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to advanced mathematics and 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
    alus
    -0.07
    azen
    -0.07
    ijken
    -0.06
    fid
    -0.06
    QualifiedName
    -0.06
     silence
    -0.06
    ypo
    -0.06
    ARAM
    -0.06
    ilerine
    -0.05
     value
    -0.05
    POSITIVE LOGITS
    UTDOWN
    0.08
    adge
    0.08
     applications
    0.07
    кид
    0.07
     theory
    0.07
     Applications
    0.07
    ÑĮко
    0.07
    enson
    0.07
    tings
    0.07
     Theory
    0.07
    Activations Density 0.070%

    No Known Activations