© 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. 88346
    Prev
    Next
    INDEX
    Explanations

    conditional phrases related to medical instructions and precautions

    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
    avar
    -0.07
    tractor
    -0.06
     radix
    -0.06
    abase
    -0.06
    ATAB
    -0.06
    abay
    -0.06
     plag
    -0.06
    okus
    -0.06
    inerary
    -0.06
    èm
    -0.06
    POSITIVE LOGITS
    cers
    0.08
    cer
    0.07
    -eslint
    0.07
    ardown
    0.07
    nech
    0.07
    ยà¸ĩ
    0.07
    heits
    0.07
    ãĤį
    0.06
    itung
    0.06
     symptoms
    0.06
    Activations Density 0.010%

    No Known Activations