© 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. 119380
    Prev
    Next
    INDEX
    Explanations

    information related to community health programs and 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
    ,
    -0.06
     world
    -0.06
     firms
    -0.06
    udic
    -0.06
     convention
    -0.06
     companies
    -0.06
     or
    -0.06
     commissions
    -0.05
    oon
    -0.05
     and
    -0.05
    POSITIVE LOGITS
     programa
    0.11
     program
    0.11
    program
    0.10
     Program
    0.10
     programme
    0.10
     programma
    0.09
    -program
    0.09
     пÑĢогÑĢамм
    0.09
     Programme
    0.09
    _program
    0.09
    Activations Density 0.059%

    No Known Activations