© 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. 17-LLAMASCOPE-RES-131K
    11. 107659
    Prev
    Next
    INDEX
    Explanations

    terms related to ethics and ethical considerations

    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
    ùa
    -0.07
    ourt
    -0.06
     mitt
    -0.06
     moz
    -0.06
     wiki
    -0.06
    ίλ
    -0.06
    _CHIP
    -0.06
     levy
    -0.06
     cuc
    -0.06
    ué
    -0.06
    POSITIVE LOGITS
     ethical
    0.11
     Ethics
    0.11
     ethics
    0.11
    ethical
    0.10
     unethical
    0.08
     ethic
    0.08
    Eth
    0.08
    .codes
    0.07
     moral
    0.07
     Bri
    0.07
    Activations Density 0.000%

    No Known Activations