© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 78213
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental and organizational structures

    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
    -0.08
    lád
    -0.08
    esson
    -0.07
    annah
    -0.07
     Higgins
    -0.07
    itele
    -0.07
    _distribution
    -0.07
    è¢ĸ
    -0.06
    ãģĭãģij
    -0.06
     Ùħعت
    -0.06
    POSITIVE LOGITS
     institution
    0.08
     entity
    0.07
     creation
    0.07
     created
    0.07
     organization
    0.07
     establishment
    0.07
    Created
    0.07
     organisation
    0.07
    eur
    0.07
     existed
    0.07
    Activations Density 0.038%

    No Known Activations