© 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. 106051
    Prev
    Next
    INDEX
    Explanations

    financial advice and suggestions related to managing money, loans, and expenses

    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
    etas
    -0.08
    æ´¥
    -0.07
    anuts
    -0.07
    ìłĿ
    -0.07
     PlzeÅĪ
    -0.07
    kup
    -0.07
    ander
    -0.07
    еÑİ
    -0.07
    ertia
    -0.07
    ẻ
    -0.07
    POSITIVE LOGITS
     borrow
    0.08
     borrowing
    0.08
    tap
    0.07
     Tap
    0.07
     sell
    0.07
     tap
    0.07
     sacrifices
    0.07
     selling
    0.07
     sale
    0.07
     sacr
    0.06
    Activations Density 0.041%

    No Known Activations