© 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. 39559
    Prev
    Next
    INDEX
    Explanations

    references to customer service and personalized marketing in retail contexts

    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
     personal
    -0.06
    ãĥ«ãĥĪ
    -0.06
     imp
    -0.06
     ni
    -0.06
    AGR
    -0.05
    personal
    -0.05
    xin
    -0.05
     Plasma
    -0.05
     >>=
    -0.05
     Pers
    -0.05
    POSITIVE LOGITS
    erosis
    0.10
    uzzer
    0.08
    ulings
    0.08
     institution
    0.08
    uggy
    0.08
     kabil
    0.08
     полиÑĤи
    0.08
     company
    0.08
    solete
    0.07
    ubbo
    0.07
    Activations Density 0.018%

    No Known Activations