© 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. 62438
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the majority in various contexts

    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
    iken
    -0.06
    åĦ
    -0.06
    mil
    -0.06
    awl
    -0.06
    ruz
    -0.06
    raz
    -0.06
    chio
    -0.05
     Weather
    -0.05
     Kirk
    -0.05
    spar
    -0.05
    POSITIVE LOGITS
     majority
    0.08
     Majority
    0.08
    gnore
    0.07
    457
    0.07
     болÑĮÑĪин
    0.07
    ancock
    0.07
    vailability
    0.06
    asename
    0.06
    buz
    0.06
     nuest
    0.06
    Activations Density 0.024%

    No Known Activations