© 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. 88998
    Prev
    Next
    INDEX
    Explanations

    elements related to arrival and scheduling

    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
    lung
    -0.06
     Cron
    -0.06
     active
    -0.06
    owe
    -0.06
     next
    -0.06
    _sensitive
    -0.06
     concept
    -0.06
    sink
    -0.06
     sink
    -0.06
     Mou
    -0.06
    POSITIVE LOGITS
     arrival
    0.16
     arriving
    0.16
     arrive
    0.16
     arrives
    0.15
     arrived
    0.15
     arrivals
    0.14
     Arrival
    0.14
    arrival
    0.13
     lleg
    0.13
     arriv
    0.12
    Activations Density 0.028%

    No Known Activations