© 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. 5-LLAMASCOPE-RES-131K
    11. 126616
    Prev
    Next
    INDEX
    Explanations

    terms related to the pharmaceutical industry and drug manufacturing

    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
    èĥŀ
    -0.07
    .central
    -0.07
    ména
    -0.07
    ä¸Ģ个人
    -0.07
     Sed
    -0.07
    _SOFT
    -0.07
    æĸ
    -0.07
     putas
    -0.06
    istrovstvÃŃ
    -0.06
    ska
    -0.06
    POSITIVE LOGITS
    OUCH
    0.06
    pray
    0.06
    agi
    0.06
    licts
    0.06
     neon
    0.06
     sustained
    0.06
    outu
    0.06
    omp
    0.06
    aps
    0.06
     supply
    0.05
    Activations Density 0.012%

    No Known Activations