© 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. 71933
    Prev
    Next
    INDEX
    Explanations

    phrases related to project validation and compliance with regulations

    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
    kus
    -0.07
    ChangedEventArgs
    -0.07
    -scal
    -0.06
     moden
    -0.06
    eview
    -0.06
    udder
    -0.06
    urga
    -0.05
     оÑĢганизма
    -0.05
     yana
    -0.05
     occ
    -0.05
    POSITIVE LOGITS
     violation
    0.11
     legality
    0.11
     violating
    0.10
     violate
    0.10
     legal
    0.10
    Violation
    0.10
    legal
    0.10
     violations
    0.10
     Viol
    0.10
     violates
    0.10
    Activations Density 0.050%

    No Known Activations