© 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. 79226
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to quantum physics and its applications

    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
    imoto
    -0.06
    .mvp
    -0.06
     lost
    -0.06
    amework
    -0.05
     being
    -0.05
    bote
    -0.05
     asym
    -0.05
     Magnum
    -0.05
     patron
    -0.05
    uhe
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.09
    systems
    0.09
     systems
    0.08
    ayar
    0.08
    subclass
    0.07
    settings
    0.07
    ington
    0.07
    å¨ĺ
    0.07
    Settings
    0.07
    oji
    0.07
    Activations Density 0.061%

    No Known Activations