© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80642
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity monitoring and threat management

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ENA
    -0.07
    RING
    -0.07
    uÄį
    -0.07
     kriz
    -0.06
    èĤ¡
    -0.06
     ########.
    -0.06
    วม
    -0.06
     emergency
    -0.06
    çĨĬ
    -0.06
     snatch
    -0.06
    POSITIVE LOGITS
     CWE
    0.08
    ÙĪرت
    0.07
     port
    0.07
    surf
    0.07
     vulnerability
    0.07
     Vulner
    0.06
    alse
    0.06
     æ¼
    0.06
    å¼±
    0.06
     risk
    0.06
    Activations Density 0.006%

    No Known Activations