© 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. 59733
    Prev
    Next
    INDEX
    Explanations

    references to cyber attacks and security breaches

    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
     Fet
    -0.08
    unsch
    -0.07
     fet
    -0.07
    riad
    -0.07
    ÅĻeb
    -0.07
     extradition
    -0.06
    arser
    -0.06
     MERCHANTABILITY
    -0.06
    åĬ©
    -0.06
    ylül
    -0.06
    POSITIVE LOGITS
     data
    0.06
     internal
    0.06
     compromise
    0.06
     storage
    0.06
    worm
    0.06
     traced
    0.06
     attack
    0.06
     system
    0.06
     computer
    0.06
    _console
    0.06
    Activations Density 0.009%

    No Known Activations