© 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. 106249
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral and ethical judgments

    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
    lero
    -0.07
    rip
    -0.07
    Ỽt
    -0.07
    _preds
    -0.06
    Å¡ti
    -0.06
    наÑĩе
    -0.06
    гл
    -0.06
    instead
    -0.06
     ضÙħÙĨ
    -0.06
     pena
    -0.06
    POSITIVE LOGITS
     physical
    0.15
    physical
    0.14
     Physical
    0.13
     overt
    0.13
     direct
    0.13
     directly
    0.12
    Physical
    0.12
    direct
    0.11
     obvious
    0.11
     physically
    0.11
    Activations Density 0.058%

    No Known Activations