© 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. 83253
    Prev
    Next
    INDEX
    Explanations

    references to charitable organizations and community initiatives

    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
    ookie
    -0.07
    xit
    -0.07
    Customers
    -0.07
    ä¸ļ
    -0.07
    oog
    -0.07
    æµģéĩı
    -0.07
    daq
    -0.07
    olumn
    -0.07
    Authorities
    -0.07
    Mvc
    -0.07
    POSITIVE LOGITS
     organization
    0.09
     Foundation
    0.08
     foundation
    0.08
     Program
    0.07
     Project
    0.07
     program
    0.07
     organisation
    0.07
     youth
    0.07
     programs
    0.07
     Action
    0.07
    Activations Density 0.142%

    No Known Activations