© 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. 89831
    Prev
    Next
    INDEX
    Explanations

    references to ethical considerations and moral dilemmas

    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
    istrovstvÃŃ
    -0.09
    è²´
    -0.08
    enties
    -0.08
    è´µ
    -0.08
    relude
    -0.07
    _mC
    -0.07
    ModelProperty
    -0.07
    stants
    -0.07
    innie
    -0.07
    aris
    -0.07
    POSITIVE LOGITS
    ighton
    0.06
    ne
    0.06
     people
    0.06
    æµħ
    0.06
     Ingen
    0.06
     young
    0.06
     Martial
    0.06
     Nations
    0.05
     deeper
    0.05
     guts
    0.05
    Activations Density 0.037%

    No Known Activations