© 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. 88933
    Prev
    Next
    INDEX
    Explanations

    terms related to protection and safety measures

    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
    मन
    -0.06
    shima
    -0.06
     Mastery
    -0.06
    ContentSize
    -0.06
     fres
    -0.06
    Alive
    -0.06
     Zw
    -0.06
     seins
    -0.06
    Locker
    -0.06
    _bridge
    -0.05
    POSITIVE LOGITS
     protection
    0.26
     Protection
    0.21
     protections
    0.20
     protect
    0.19
    ä¿ĿæĬ¤
    0.19
     protecting
    0.18
    Protection
    0.18
     protects
    0.17
     protected
    0.17
     protective
    0.16
    Activations Density 0.068%

    No Known Activations