© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84852
    Prev
    Next
    INDEX
    Explanations

    themes related to labor and work-related discussions

    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
    igen
    -0.07
    yen
    -0.07
    ookie
    -0.07
    ckill
    -0.07
    OwnProperty
    -0.07
    styleType
    -0.06
    bulan
    -0.06
    _EVT
    -0.06
    arti
    -0.06
    QRST
    -0.06
    POSITIVE LOGITS
    erman
    0.07
    imulator
    0.06
    urn
    0.06
     welcomed
    0.06
    785
    0.06
    774
    0.06
    uter
    0.06
    iley
    0.06
     Yourself
    0.06
    yla
    0.06
    Activations Density 0.013%

    No Known Activations