© 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 EvalsExportsinterp-engineNEWAPI 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. 93024
    Prev
    Next
    INDEX
    Explanations

    keywords related to aviation and flight operations

    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
    elmet
    -0.07
    roups
    -0.06
    eno
    -0.06
     nhé
    -0.06
    ίδα
    -0.06
    ients
    -0.06
    ellular
    -0.06
    òa
    -0.06
     testimon
    -0.06
     sıras
    -0.06
    POSITIVE LOGITS
     has
    0.07
    hra
    0.06
     wasn
    0.06
    apollo
    0.06
     was
    0.06
     hasn
    0.06
    unden
    0.06
    agate
    0.06
    ovy
    0.06
    Kat
    0.06
    Activations Density 0.058%

    No Known Activations