© 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. 15-LLAMASCOPE-RES-131K
    11. 62417
    Prev
    Next
    INDEX
    Explanations

    phrases related to the willingness to endure hardship or make sacrifices

    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
    raž
    -0.07
    esture
    -0.07
    ercial
    -0.07
    etxt
    -0.07
    atten
    -0.07
    ÐľÐŀ
    -0.06
    .me
    -0.06
    earn
    -0.06
    Ease
    -0.06
     mest
    -0.06
    POSITIVE LOGITS
     Prosper
    0.07
     slightly
    0.07
     sacrifice
    0.06
    é¡ĺ
    0.06
    Py
    0.06
     somewhat
    0.06
     sacr
    0.06
    çī
    0.06
    tol
    0.06
    130
    0.06
    Activations Density 0.014%

    No Known Activations