© 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. 17-LLAMASCOPE-RES-131K
    11. 130175
    Prev
    Next
    INDEX
    Explanations

    terms associated with themes of moral judgment and religious beliefs

    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
    Msp
    -0.07
    ç»į
    -0.07
    è¼
    -0.06
    .SpringApplication
    -0.06
     rumpe
    -0.06
    ëŀĻ
    -0.06
     outliers
    -0.06
    amina
    -0.06
    maps
    -0.06
    ishops
    -0.06
    POSITIVE LOGITS
     pag
    0.07
    azzi
    0.07
     compromise
    0.06
     ид
    0.06
    opy
    0.06
     entr
    0.06
     counterfeit
    0.06
     sor
    0.06
     Modal
    0.06
     False
    0.06
    Activations Density 0.089%

    No Known Activations