© 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. 118054
    Prev
    Next
    INDEX
    Explanations

    themes related to challenging social norms and conventions

    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
    rana
    -0.07
    /live
    -0.06
    DEC
    -0.06
    dup
    -0.06
    roup
    -0.06
    enal
    -0.06
    estre
    -0.06
    ÙĨب
    -0.06
    celed
    -0.06
     pending
    -0.06
    POSITIVE LOGITS
     altogether
    0.07
     conventional
    0.07
     restr
    0.07
     conventions
    0.07
     convention
    0.07
     challeng
    0.07
    -alist
    0.07
    alto
    0.06
     traditional
    0.06
     expectations
    0.06
    Activations Density 0.022%

    No Known Activations