© 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. 129258
    Prev
    Next
    INDEX
    Explanations

    complex medical terminology or related concepts

    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
    βα
    -0.06
    PCS
    -0.06
    eer
    -0.06
    ῶ
    -0.06
    WR
    -0.06
    èĤ
    -0.05
     jedna
    -0.05
    ted
    -0.05
    etes
    -0.05
    âĢ¦)↵↵
    -0.05
    POSITIVE LOGITS
    ului
    0.08
     of
    0.08
    acionales
    0.08
    екÑĤоÑĢа
    0.07
    .Guna
    0.07
    ового
    0.07
    elopment
    0.07
     của
    0.07
    ủa
    0.07
    StackNavigator
    0.07
    Activations Density 0.052%

    No Known Activations