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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 70639
    Prev
    Next
    INDEX
    Explanations

    key terms related to healthcare services and patient engagement technology

    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
     Perf
    -0.06
    ledge
    -0.06
    ÂĪ
    -0.06
     pam
    -0.05
     crashes
    -0.05
     Ung
    -0.05
    é³
    -0.05
     wreck
    -0.05
    658
    -0.05
     exponent
    -0.05
    POSITIVE LOGITS
    noun
    0.07
    -chat
    0.07
    æĥ
    0.07
    ï¸
    0.07
    /chat
    0.07
    иж
    0.07
    utterstock
    0.07
    idian
    0.07
    éļ
    0.07
    .chat
    0.07
    Activations Density 0.002%

    No Known Activations