© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 264
    Prev
    Next
    INDEX
    Explanations

    mentions of locations and context for various systems or entities

    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
     Äijâu
    -0.07
    utsch
    -0.06
    :CGRect
    -0.06
     Symbols
    -0.06
     tuyá»ĥn
    -0.06
     Cruise
    -0.06
    PCS
    -0.06
    icens
    -0.06
    ink
    -0.06
     selection
    -0.06
    POSITIVE LOGITS
     most
    0.07
     addslashes
    0.07
    most
    0.06
    à¥ģà¤ļ
    0.06
    vido
    0.06
    ]={↵
    0.06
    ê´
    0.06
    askell
    0.06
    å°ıæĹ¶
    0.06
    ÏĦÎŃ
    0.06
    Activations Density 0.012%

    No Known Activations