© 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. 1240
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant moments or circumstances relating to timing and opportunity

    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
    604
    -0.07
    abin
    -0.07
    inkel
    -0.06
     Colbert
    -0.06
    agnar
    -0.06
    ucken
    -0.06
    248
    -0.06
    ÑĪин
    -0.06
    .YesNo
    -0.06
    TouchEvent
    -0.06
    POSITIVE LOGITS
     timing
    0.14
     Timing
    0.12
     coinc
    0.10
    timing
    0.10
    Timing
    0.10
     coincide
    0.09
     timings
    0.09
     Coin
    0.09
     coincidence
    0.08
    Tim
    0.08
    Activations Density 0.033%

    No Known Activations