© 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. 3595
    Prev
    Next
    INDEX
    Explanations

    references to cybersecurity threats and precautions

    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
    itori
    -0.07
     stringWith
    -0.07
    stants
    -0.07
    ì¹Ļ
    -0.07
     NavParams
    -0.07
    анÑĤа
    -0.07
    ìĿ´íĦ°
    -0.07
    CCR
    -0.07
    unte
    -0.07
    ÑĢÑĥб
    -0.07
    POSITIVE LOGITS
    ives
    0.07
     exploitation
    0.06
     political
    0.06
     privacy
    0.06
     predators
    0.06
    obs
    0.06
     discrimination
    0.06
    hw
    0.06
     potential
    0.06
     Privacy
    0.06
    Activations Density 0.042%

    No Known Activations