© 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. 71619
    Prev
    Next
    INDEX
    Explanations

    phrases related to delays and processing times

    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
     preempt
    -0.07
    ouston
    -0.07
    Readable
    -0.07
    adero
    -0.07
    retty
    -0.07
    eni
    -0.07
    uele
    -0.06
    bero
    -0.06
    gis
    -0.06
    laus
    -0.06
    POSITIVE LOGITS
     access
    0.08
     get
    0.07
     processing
    0.07
     response
    0.07
    itespace
    0.06
     promised
    0.06
    ulumi
    0.06
     Specialty
    0.06
     process
    0.06
     resolution
    0.06
    Activations Density 0.017%

    No Known Activations