© 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. 92791
    Prev
    Next
    INDEX
    Explanations

    instances of emergency landings and related aviation events

    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
    roduced
    -0.07
     Fallen
    -0.07
    stell
    -0.06
    交éĢļ
    -0.06
     accessory
    -0.06
    .scalablytyped
    -0.06
     Falling
    -0.06
     types
    -0.06
     ful
    -0.06
     Chow
    -0.06
    POSITIVE LOGITS
    çıŃ
    0.08
    èĩ´
    0.07
     Palette
    0.07
     skoro
    0.07
     InvalidArgumentException
    0.07
    ilha
    0.06
    åĿª
    0.06
    oper
    0.06
    redit
    0.06
     sched
    0.06
    Activations Density 0.008%

    No Known Activations