© 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. 57523
    Prev
    Next
    INDEX
    Explanations

    expressions related to unforgettable memories and significant life 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
    èĪ
    -0.08
    evin
    -0.07
    omi
    -0.06
    eri
    -0.06
     nem
    -0.06
    habi
    -0.06
     su
    -0.06
    District
    -0.06
    .utilities
    -0.06
     Bek
    -0.06
    POSITIVE LOGITS
     forever
    0.11
    æ°¸
    0.08
     lifelong
    0.08
    æ°¸ä¹ħ
    0.08
     Forever
    0.07
    Forever
    0.07
     lifetime
    0.07
     memories
    0.07
    privileged
    0.07
    anja
    0.06
    Activations Density 0.014%

    No Known Activations