© 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. 95319
    Prev
    Next
    INDEX
    Explanations

    concepts related to suitability or fitness for specific purposes or roles

    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
    å¼ı
    -0.07
    ODEV
    -0.07
    sis
    -0.06
    átis
    -0.06
    itis
    -0.06
    itus
    -0.06
    indre
    -0.06
    kes
    -0.06
     sclerosis
    -0.06
    ADS
    -0.06
    POSITIVE LOGITS
    geries
    0.07
    κÏħ
    0.07
    ProcessEvent
    0.07
     deliberate
    0.06
    ably
    0.06
    teki
    0.06
    ãģ¹ãģį
    0.06
    -for
    0.06
    /qt
    0.06
    خش
    0.06
    Activations Density 0.008%

    No Known Activations