© 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. 62339
    Prev
    Next
    INDEX
    Explanations

    references to luggage and airline baggage policies

    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
     backing
    -0.07
    TEL
    -0.06
    kre
    -0.06
    lesai
    -0.06
     indoors
    -0.06
     Compound
    -0.06
     Floating
    -0.06
    Lic
    -0.06
     inv
    -0.06
    903
    -0.05
    POSITIVE LOGITS
     Carry
    0.09
     carried
    0.09
    carry
    0.08
     carry
    0.08
     Airlines
    0.08
     charge
    0.08
     baggage
    0.07
    帯
    0.07
     Dimensions
    0.07
     æ¹
    0.07
    Activations Density 0.002%

    No Known Activations