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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5409
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement activities and legal proceedings

    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
    PÅĻi
    -0.07
    emas
    -0.07
     Rai
    -0.07
    ãĥĥãĤ«ãĥ¼
    -0.07
    cko
    -0.07
     =$
    -0.06
    à¸Ļาà¸Ķ
    -0.06
     пÑĢоÑĤÑıж
    -0.06
    579
    -0.06
    Łèĥ½
    -0.06
    POSITIVE LOGITS
     sources
    0.08
     spokes
    0.08
     âĸĪâĸĪâĸĪâĸĪâĸĪ
    0.08
     spokesperson
    0.07
     spokesman
    0.07
     spokeswoman
    0.07
     recent
    0.07
     Sources
    0.07
     âĸĪâĸĪ
    0.07
     popular
    0.06
    Activations Density 0.023%

    No Known Activations