© 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. 75249
    Prev
    Next
    INDEX
    Explanations

    concepts related to workers' compensation and related benefits

    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
    ãģ£ãģį
    -0.07
    amily
    -0.07
    icÃŃ
    -0.07
     kıl
    -0.07
    Ùħا
    -0.07
    гал
    -0.07
    ITTE
    -0.07
    ÑĢава
    -0.07
    VID
    -0.07
    voke
    -0.07
    POSITIVE LOGITS
    nel
    0.07
     crib
    0.07
    OpenHelper
    0.07
     insurance
    0.06
     laws
    0.06
    393
    0.06
     literature
    0.06
    -rel
    0.06
    oeff
    0.05
    idan
    0.05
    Activations Density 0.003%

    No Known Activations