© 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. 77229
    Prev
    Next
    INDEX
    Explanations

    concepts related to ethical theories and moral principles

    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
     Cah
    -0.08
    nev
    -0.08
    Zen
    -0.07
     mys
    -0.07
    Abr
    -0.07
     Redistribution
    -0.06
    íķĦ
    -0.06
    ubu
    -0.06
    /Index
    -0.06
     Zen
    -0.06
    POSITIVE LOGITS
     Euler
    0.07
     Delaware
    0.07
     Thomson
    0.07
     Gauss
    0.07
     Philadelphia
    0.06
    178
    0.06
     Ohio
    0.06
     Philly
    0.06
     Pennsylvania
    0.06
     Freem
    0.06
    Activations Density 0.001%

    No Known Activations