© 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. 128033
    Prev
    Next
    INDEX
    Explanations

    words related to medications and their effects

    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
    eut
    -0.06
    sterol
    -0.06
    efault
    -0.06
     Tooth
    -0.06
    coli
    -0.06
    meler
    -0.06
     Rosenstein
    -0.06
    Extension
    -0.06
    ALS
    -0.06
    иÑĢа
    -0.06
    POSITIVE LOGITS
     inert
    0.08
    opi
    0.07
    oho
    0.07
    imli
    0.07
     heroin
    0.07
     Hopkins
    0.06
    éĤ¦
    0.06
     longer
    0.06
    orro
    0.06
     SAM
    0.06
    Activations Density 0.001%

    No Known Activations