© 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. 75524
    Prev
    Next
    INDEX
    Explanations

    phrases related to injury and medical conditions

    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
    ekim
    -0.08
    ói
    -0.07
    (strict
    -0.07
    æk
    -0.07
    kün
    -0.07
    ault
    -0.07
    ://{
    -0.07
    guild
    -0.07
    ypse
    -0.07
    inkle
    -0.06
    POSITIVE LOGITS
    isch
    0.07
     ingest
    0.06
     Trend
    0.06
     critical
    0.06
     grave
    0.06
     Update
    0.06
     vital
    0.06
    305
    0.06
     Bauer
    0.06
     updateTime
    0.06
    Activations Density 0.007%

    No Known Activations