© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71991
    Prev
    Next
    INDEX
    Explanations

    medical drug names and their associated 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
    esen
    -0.07
    adas
    -0.06
     Dynasty
    -0.06
    roud
    -0.06
    umen
    -0.06
    lash
    -0.05
     Dent
    -0.05
    hod
    -0.05
     Goods
    -0.05
    wh
    -0.05
    POSITIVE LOGITS
    ®,
    0.08
     brand
    0.08
    -brand
    0.08
    ®
    0.08
    ãĤº
    0.07
     Ñģеб
    0.07
    plusplus
    0.07
    .simps
    0.07
    emons
    0.07
     çı
    0.07
    Activations Density 0.013%

    No Known Activations