© 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. 85397
    Prev
    Next
    INDEX
    Explanations

    terms related to adversarial attacks and techniques in artificial intelligence

    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
    989
    -0.07
    ditor
    -0.06
     Ster
    -0.06
    iges
    -0.06
    _decay
    -0.06
     baiser
    -0.06
    STER
    -0.06
    åĨµ
    -0.06
    iert
    -0.06
    \Id
    -0.06
    POSITIVE LOGITS
     attack
    0.08
     attacks
    0.07
     Byz
    0.07
     advers
    0.07
    ourg
    0.07
     pert
    0.06
    attack
    0.06
     addCriterion
    0.06
    кÑĢа
    0.06
    ĽĪ
    0.06
    Activations Density 0.007%

    No Known Activations