© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28598
    Prev
    Next
    INDEX
    Explanations

    references to contracts, agreements, and organizational structures within a military or governmental context

    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
    er
    -0.07
    é¦
    -0.07
    anh
    -0.07
     Ease
    -0.07
    qua
    -0.07
    ük
    -0.06
    sek
    -0.06
    inya
    -0.06
    Ú¯ÙĪ
    -0.06
    Ease
    -0.06
    POSITIVE LOGITS
    iggs
    0.07
    lopedia
    0.07
    ÅĤu
    0.06
    namen
    0.06
    .pkg
    0.06
    bate
    0.06
    ضاÙĨ
    0.06
     sting
    0.06
    ÙĪاء
    0.06
    toi
    0.06
    Activations Density 0.052%

    No Known Activations