© 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. 118172
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal expectations and various forms of evaluation or judgment

    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
    ÃĹ↵↵
    -0.07
    enga
    -0.07
    åİŁæľ¬
    -0.07
    اÙĦت
    -0.07
    tej
    -0.07
    villa
    -0.07
    ãĥ©ãĤ¤ãĥ³
    -0.07
    ohl
    -0.07
    xic
    -0.07
     WithEvents
    -0.06
    POSITIVE LOGITS
     people
    0.09
    people
    0.08
     People
    0.07
     things
    0.07
    /people
    0.07
     Things
    0.07
     stuff
    0.07
     sometimes
    0.07
    Things
    0.07
     PEOPLE
    0.07
    Activations Density 0.126%

    No Known Activations