© 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. 40917
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and security protocols

    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
    ses
    -0.07
    side
    -0.07
    ylon
    -0.07
    خاÙĨÙĩ
    -0.07
    ëŀij
    -0.06
    είÏĦε
    -0.06
    жд
    -0.06
    ph
    -0.06
    kur
    -0.06
    uy
    -0.06
    POSITIVE LOGITS
     rằng
    0.11
    876
    0.08
     that
    0.08
     bahwa
    0.08
    eru
    0.08
    that
    0.07
    oucher
    0.07
    ÑģÑĮ
    0.07
    ments
    0.07
    /prom
    0.07
    Activations Density 0.016%

    No Known Activations