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. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72597
    Prev
    Next
    INDEX
    Explanations

    mentions of North Korean leaders, particularly Kim Jong-un

    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
    Offline
    -0.07
    avo
    -0.06
     TCHAR
    -0.06
    ableView
    -0.06
    981
    -0.06
    sher
    -0.06
    ÙĪØ¨ÛĮ
    -0.06
     éĹ
    -0.06
     Am
    -0.06
    à¥Ĥह
    -0.06
    POSITIVE LOGITS
    esan
    0.07
    imeo
    0.07
    uide
    0.07
    ilha
    0.07
    å¯Ĵ
    0.06
    dh
    0.06
    anas
    0.06
    ãĤ¤ãĥ«
    0.06
    &r
    0.06
     dipped
    0.06
    Activations Density 0.001%

    No Known Activations