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

    Neuronpedia

    Jacobian LensNEW
    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. 57344
    Prev
    Next
    INDEX
    Explanations

    terms related to drug delivery and genetic engineering

    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
    asan
    -0.08
     Soros
    -0.06
     unfit
    -0.06
    ª
    -0.06
    817
    -0.06
    -0.06
    139
    -0.05
    ViewItem
    -0.05
    inos
    -0.05
     screen
    -0.05
    POSITIVE LOGITS
     delivery
    0.11
     доÑģÑĤав
    0.10
     Delivery
    0.10
     delivering
    0.09
    delivery
    0.09
     deliver
    0.08
    Delivery
    0.08
     delivered
    0.08
    _delivery
    0.08
    ütün
    0.08
    Activations Density 0.005%

    No Known Activations