© 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 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. 56068
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the interaction between concepts or ideas in a complex system

    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
    ãĤ¡
    -0.07
    usher
    -0.06
    ICollectionView
    -0.06
    é©
    -0.06
    zdy
    -0.06
    ega
    -0.06
    vert
    -0.06
     Seymour
    -0.06
     Pulse
    -0.06
    leDb
    -0.06
    POSITIVE LOGITS
     equation
    0.09
     equations
    0.08
     consideration
    0.08
    ettel
    0.07
    èĢĥ
    0.07
    ornado
    0.06
     søker
    0.06
    ijkstra
    0.06
    oner
    0.06
     excer
    0.06
    Activations Density 0.030%

    No Known Activations