Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5696
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to environmental and sustainability issues

    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
    DATED
    -0.07
    ãĤ´ãĥª
    -0.07
    _Description
    -0.07
     é«
    -0.07
     ÑģпиÑģ
    -0.07
     EÅŁ
    -0.07
    اسÙĩ
    -0.07
    à¹ģล
    -0.07
     Îĺε
    -0.07
    urette
    -0.06
    POSITIVE LOGITS
    202
    0.07
    chal
    0.06
    qw
    0.06
    ision
    0.06
     vision
    0.06
    201
    0.06
    321
    0.06
     loc
    0.06
     future
    0.06
     multi
    0.06
    Activations Density 0.028%

    No Known Activations