© 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. 72513
    Prev
    Next
    INDEX
    Explanations

    information related to airline announcements and seasonal menu offerings

    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
     compound
    -0.06
    577
    -0.06
    ziej
    -0.06
    aison
    -0.06
    compound
    -0.06
    lotte
    -0.06
    ilder
    -0.06
     Compound
    -0.06
     Mort
    -0.05
    autos
    -0.05
    POSITIVE LOGITS
     cabin
    0.09
     passengers
    0.09
     Cabin
    0.08
     Passenger
    0.08
     cockpit
    0.08
     боÑĢ
    0.08
     passenger
    0.08
    IFE
    0.07
     aisle
    0.07
    oloj
    0.07
    Activations Density 0.012%

    No Known Activations