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. 5002
    Prev
    Next
    INDEX
    Explanations

    terms related to equity and investments

    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
    zers
    -0.08
    emachine
    -0.07
    SPARENT
    -0.07
    &type
    -0.07
    æĻ´
    -0.07
     sem
    -0.07
    .SuspendLayout
    -0.07
    779
    -0.07
    quet
    -0.06
    .shtml
    -0.06
    POSITIVE LOGITS
    ades
    0.08
     suk
    0.06
    mony
    0.06
    riel
    0.06
    /div
    0.06
    mand
    0.06
     Alv
    0.06
    4
    0.06
    /assets
    0.06
    ogen
    0.05
    Activations Density 0.006%

    No Known Activations