© 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. 89636
    Prev
    Next
    INDEX
    Explanations

    phrases related to travel and flight bookings

    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
    车
    -0.06
     jenter
    -0.06
    _mt
    -0.06
    è»Ĭ
    -0.06
    hift
    -0.06
    ôm
    -0.06
    ÙĪرا
    -0.06
    ĵåIJį
    -0.06
     Lor
    -0.06
    omor
    -0.06
    POSITIVE LOGITS
     flight
    0.10
     air
    0.09
     Fly
    0.09
     flying
    0.08
    Fly
    0.08
    air
    0.08
     landing
    0.08
     пеÑĢел
    0.08
     flights
    0.08
     Flight
    0.08
    Activations Density 0.022%

    No Known Activations