© 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. 15-LLAMASCOPE-RES-131K
    11. 27177
    Prev
    Next
    INDEX
    Explanations

    phrases related to diversity and representation in literature and publishing

    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
    TagName
    -0.06
    reeNode
    -0.06
    UTO
    -0.06
    ATAR
    -0.06
    utas
    -0.06
    rik
    -0.06
    ContentAlignment
    -0.06
    ÑĥÑĪки
    -0.06
     life
    -0.06
    _UNKNOWN
    -0.06
    POSITIVE LOGITS
     industry
    0.09
     Industry
    0.08
    industry
    0.07
     corporations
    0.06
    è¯Ŀ
    0.06
     eyeb
    0.06
     companies
    0.06
    è¡Įä¸ļ
    0.06
    @Resource
    0.06
     αÏĨ
    0.06
    Activations Density 0.041%

    No Known Activations