© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16210
    Prev
    Next
    INDEX
    Explanations

    references to pharmaceuticals, particularly focusing on specific drugs and their dosage information

    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
     transparent
    -0.07
    lemen
    -0.07
    chain
    -0.07
    xon
    -0.06
    strand
    -0.06
    vida
    -0.06
    ngen
    -0.06
    ips
    -0.06
    nesc
    -0.06
    arat
    -0.06
    POSITIVE LOGITS
    -online
    0.09
    _online
    0.09
     online
    0.08
    à¸Ńà¸Ńà¸Ļà¹Ħลà¸Ļ
    0.07
    online
    0.07
    \Migration
    0.07
     Online
    0.07
     ONLINE
    0.07
     ì͍
    0.07
    Online
    0.07
    Activations Density 0.004%

    No Known Activations