© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84943
    Prev
    Next
    INDEX
    Explanations

    descriptions related to flight training and aviation careers

    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
    .volley
    -0.07
    otti
    -0.07
    mtree
    -0.07
    ForRow
    -0.07
    ãĥ³ãĥĩ
    -0.07
    ardo
    -0.06
    gran
    -0.06
    arda
    -0.06
    xdd
    -0.06
    HLT
    -0.06
    POSITIVE LOGITS
     Pilot
    0.09
     pilot
    0.09
     pil
    0.08
     simulator
    0.08
     Tower
    0.08
     tower
    0.08
     pilots
    0.08
     crew
    0.07
     Crew
    0.07
     training
    0.07
    Activations Density 0.012%

    No Known Activations