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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5055
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases associated with regulations or formal documents

    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
    con
    -0.09
    -con
    -0.08
    DBObject
    -0.08
    -Con
    -0.07
    isu
    -0.07
    is
    -0.07
    _con
    -0.07
    ists
    -0.07
    ob
    -0.07
    istr
    -0.07
    POSITIVE LOGITS
    ئ
    0.07
    reo
    0.07
     Elev
    0.07
     sos
    0.07
    erin
    0.07
    ar
    0.06
    寧
    0.06
    ÑĥÑĪки
    0.06
    -tm
    0.06
     sey
    0.06
    Activations Density 0.326%

    No Known Activations