© 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. 75995
    Prev
    Next
    INDEX
    Explanations

    terms related to security measures and protection layers in technology

    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
    hurst
    -0.07
     frem
    -0.06
    thon
    -0.06
    uchos
    -0.06
    norm
    -0.06
    اÙĤ
    -0.06
     необ
    -0.06
     restrained
    -0.06
     norm
    -0.06
    623
    -0.06
    POSITIVE LOGITS
     protection
    0.17
     protecting
    0.13
     protect
    0.13
     Protection
    0.13
    protect
    0.12
     protective
    0.12
     protects
    0.12
     defense
    0.11
     Protect
    0.11
     against
    0.11
    Activations Density 0.053%

    No Known Activations