© 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. 5-LLAMASCOPE-RES-131K
    11. 126983
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fired" or related terms in contexts involving termination or dismissal

    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
    abo
    -0.09
    .twig
    -0.07
     Coy
    -0.07
     taxing
    -0.07
    unma
    -0.07
    arrera
    -0.06
    lesh
    -0.06
    mour
    -0.06
    Extractor
    -0.06
     discourse
    -0.06
    POSITIVE LOGITS
     Lor
    0.07
    IMER
    0.07
    GLE
    0.06
    orse
    0.06
    erson
    0.06
    /loose
    0.06
    imer
    0.06
    ewidth
    0.06
     khá»ıi
    0.06
    ose
    0.06
    Activations Density 0.014%

    No Known Activations