© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75302
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational protocols and 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
     Khoa
    -0.07
    583
    -0.06
    łģ
    -0.06
    mid
    -0.06
     navigationOptions
    -0.06
     ÑĤов
    -0.06
     اÙģت
    -0.06
    933
    -0.06
    Forum
    -0.06
     ìłĢ
    -0.06
    POSITIVE LOGITS
     system
    0.09
     approach
    0.09
     scheme
    0.08
    ocator
    0.07
    istema
    0.07
     sliding
    0.07
     model
    0.07
    appro
    0.07
     systems
    0.06
     concept
    0.06
    Activations Density 0.156%

    No Known Activations