© 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. 9-LLAMASCOPE-RES-131K
    11. 94416
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to appointments and roles in organizations

    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
    elsinki
    -0.06
    ardo
    -0.06
    adas
    -0.06
    ensen
    -0.06
    egen
    -0.06
    XmlAttribute
    -0.05
     lust
    -0.05
    Abr
    -0.05
    -Fi
    -0.05
    ARE
    -0.05
    POSITIVE LOGITS
    maal
    0.07
    ÑĥÑĤи
    0.07
     McKin
    0.06
    éħ
    0.06
     Jr
    0.06
    illon
    0.06
    ÚĺÙĨ
    0.06
     ruh
    0.06
    orest
    0.06
    ignty
    0.06
    Activations Density 0.008%

    No Known Activations