© 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. 9-LLAMASCOPE-RES-131K
    11. 96234
    Prev
    Next
    INDEX
    Explanations

    references to data management and optimization techniques

    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
     tri
    -0.06
    ano
    -0.06
     arch
    -0.06
     Helena
    -0.05
     operated
    -0.05
    -oper
    -0.05
     b
    -0.05
    ãĤ¯ãĤ»
    -0.05
     ca
    -0.05
    Kal
    -0.05
    POSITIVE LOGITS
    Äįin
    0.07
    undi
    0.07
    ildo
    0.07
    emit
    0.07
    emek
    0.07
    èİİ
    0.07
     VÅ¡ech
    0.07
    ovÃŃ
    0.07
    comed
    0.07
    /DTD
    0.06
    Activations Density 0.098%

    No Known Activations