© 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 EvalsExportsinterp-engineNEWAPI 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. 108353
    Prev
    Next
    INDEX
    Explanations

    references to drug-related terms and comparisons

    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
    phas
    -0.06
    keh
    -0.06
    åĽ²
    -0.06
     Antar
    -0.06
     Rebellion
    -0.06
    lass
    -0.06
    Spark
    -0.06
     Mineral
    -0.06
    ystone
    -0.06
     Spark
    -0.06
    POSITIVE LOGITS
    entanyl
    0.07
     lethal
    0.06
    éli
    0.06
    ynos
    0.06
    owi
    0.06
     mixing
    0.06
    sched
    0.06
    кÑĢа
    0.06
    ãģķãĤī
    0.06
    chem
    0.06
    Activations Density 0.002%

    No Known Activations