© 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. 126004
    Prev
    Next
    INDEX
    Explanations

    references to reflections and reminders of important values and experiences

    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
    ivant
    -0.08
     Incoming
    -0.07
    iÄįka
    -0.06
    _TestCase
    -0.06
    atsapp
    -0.06
    _SCL
    -0.06
     Trend
    -0.06
     Sever
    -0.06
    elor
    -0.06
     кÑĥлÑĮ
    -0.06
    POSITIVE LOGITS
     remind
    0.08
     forgotten
    0.07
     why
    0.07
     reminder
    0.07
     how
    0.07
     important
    0.07
     importance
    0.07
    .scalablytyped
    0.07
     reminding
    0.07
     reminded
    0.06
    Activations Density 0.017%

    No Known Activations