© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    topics related to airport security and the challenges it presents

    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
     houses
    -0.06
    quake
    -0.06
     m
    -0.06
    indow
    -0.06
     stable
    -0.06
     stock
    -0.05
    çĤ
    -0.05
    dro
    -0.05
    ships
    -0.05
     aut
    -0.05
    POSITIVE LOGITS
    airport
    0.09
     airport
    0.09
     Airport
    0.09
    Airport
    0.09
     airports
    0.09
    -security
    0.09
    _security
    0.08
     Terrorism
    0.08
     screening
    0.08
    æľºåľº
    0.08
    Activations Density 0.013%

    No Known Activations