© 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. 127112
    Prev
    Next
    INDEX
    Explanations

    terminology related to apps, services, and features in the context of online tools or resources

    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
    son
    -0.06
    core
    -0.06
    leen
    -0.05
     entire
    -0.05
    adi
    -0.05
    rats
    -0.05
     th
    -0.05
    -ca
    -0.05
    point
    -0.05
     tym
    -0.05
    POSITIVE LOGITS
    unger
    0.08
    ÙĪÙĬ
    0.08
    ikut
    0.07
    ulfilled
    0.07
     BaseController
    0.07
     handy
    0.07
     supplied
    0.07
    agy
    0.07
    mlink
    0.07
     PROVIDED
    0.07
    Activations Density 0.016%

    No Known Activations