© 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 EvalsExportsinterp-engineNEWAPI 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. 72405
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to protection and guarding

    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
    vil
    -0.07
    wan
    -0.06
     restraint
    -0.06
    -0.06
    aky
    -0.06
    oran
    -0.06
     Bracket
    -0.06
    abel
    -0.06
    okino
    -0.06
    807
    -0.06
    POSITIVE LOGITS
    protect
    0.12
     protect
    0.12
     protecting
    0.11
     je
    0.11
    guard
    0.11
     protective
    0.11
     guard
    0.11
     safeguard
    0.11
     protects
    0.11
    -guard
    0.11
    Activations Density 0.090%

    No Known Activations