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

    Neuronpedia

    Jacobian LensNEW
    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. 93825
    Prev
    Next
    INDEX
    Explanations

    references to government and security-related structures

    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
    égor
    -0.07
    pta
    -0.07
    δή
    -0.07
    avanaugh
    -0.06
    eties
    -0.06
    ẽ
    -0.06
    enderit
    -0.06
    aupt
    -0.06
    iseum
    -0.06
    ç»Ń
    -0.06
    POSITIVE LOGITS
     Foreign
    0.08
     Advis
    0.07
    Cipher
    0.07
     Intelligence
    0.07
    Foreign
    0.07
     Leak
    0.07
     cables
    0.06
    andan
    0.06
     cabinet
    0.06
     prime
    0.06
    Activations Density 0.005%

    No Known Activations