© 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 EvalsExportsAPI 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. 58652
    Prev
    Next
    INDEX
    Explanations

    expressions of punctuality and professionalism in service experiences

    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
     Kop
    -0.08
    asting
    -0.07
    afil
    -0.07
    tember
    -0.07
    Scanner
    -0.07
    .SelectedItems
    -0.07
    razy
    -0.06
    lit
    -0.06
    енÑģ
    -0.06
    elong
    -0.06
    POSITIVE LOGITS
     visits
    0.09
     visit
    0.09
     visita
    0.08
     arrival
    0.08
     appointment
    0.08
     appointments
    0.08
     arrive
    0.07
     visited
    0.07
     visite
    0.07
     방문
    0.07
    Activations Density 0.017%

    No Known Activations