© 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. 15-LLAMASCOPE-RES-131K
    11. 27675
    Prev
    Next
    INDEX
    Explanations

    symbols and numerical representations related to data and calculations

    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
    alles
    -0.07
     تÙĪ
    -0.06
    tÃŃ
    -0.06
    affer
    -0.06
    Obsolete
    -0.06
    ebek
    -0.06
     sám
    -0.06
    )./
    -0.06
    -lite
    -0.06
    anka
    -0.06
    POSITIVE LOGITS
    ajo
    0.07
    okino
    0.07
    ë
    0.07
    ê±°ëĤĺ
    0.06
    Ìģ
    0.06
    plib
    0.06
    createClass
    0.06
    ota
    0.06
    andel
    0.06
    ophilia
    0.06
    Activations Density 0.030%

    No Known Activations