© 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. 125521
    Prev
    Next
    INDEX
    Explanations

    phrases related to monitoring and tracking performance or activity

    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
    	Copyright
    -0.07
    wil
    -0.07
    ajar
    -0.07
    Advertisement
    -0.07
    ledo
    -0.07
    slaught
    -0.07
    à¹Ģà¸Ł
    -0.06
    AndGet
    -0.06
    éf
    -0.06
    summ
    -0.06
    POSITIVE LOGITS
     purchases
    0.07
     purchase
    0.07
     purchased
    0.06
     Buying
    0.06
     bought
    0.06
    æ¼ı
    0.06
    urchase
    0.06
     annually
    0.06
     costly
    0.06
    anger
    0.06
    Activations Density 0.008%

    No Known Activations