© 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. 17-LLAMASCOPE-RES-131K
    6. 55422
    Prev
    Next
    INDEX
    Explanations

    terms related to high-value auction items

    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
     Fourth
    -0.06
    493
    -0.06
     CircularProgress
    -0.06
    Stores
    -0.06
    kinson
    -0.06
     Holl
    -0.06
    (æĹ¥
    -0.06
    æĺŃ
    -0.06
     disc
    -0.06
    538
    -0.06
    POSITIVE LOGITS
     items
    0.08
     bidding
    0.07
     cons
    0.07
     item
    0.07
    items
    0.07
     ìĿ´ë²Ī
    0.07
    )section
    0.07
    ondheim
    0.07
    _dma
    0.06
    Rare
    0.06
    Activations Density 0.002%

    No Known Activations