© 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. 74552
    Prev
    Next
    INDEX
    Explanations

    references to searches and legal procedures related to law enforcement

    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
    istrovstvÃŃ
    -0.07
     fatt
    -0.06
    ccione
    -0.06
    골
    -0.06
    丸
    -0.06
    entiful
    -0.06
    akens
    -0.06
     splash
    -0.06
    ĭ
    -0.06
    [mask
    -0.06
    POSITIVE LOGITS
     searching
    0.08
     searcher
    0.07
     searched
    0.07
     contents
    0.07
     search
    0.07
     Searches
    0.07
     Contents
    0.07
    Contents
    0.07
    -search
    0.07
    /Search
    0.07
    Activations Density 0.015%

    No Known Activations