© 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. 78936
    Prev
    Next
    INDEX
    Explanations

    mentions of battery levels and charging systems

    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
    omy
    -0.06
     Shack
    -0.06
    åĿĢ
    -0.06
    asca
    -0.06
     widened
    -0.06
     widest
    -0.06
    iper
    -0.06
     cancelled
    -0.06
    oce
    -0.06
    MOOTH
    -0.06
    POSITIVE LOGITS
     reserves
    0.12
     depleted
    0.12
     depletion
    0.12
     stocks
    0.10
     dwind
    0.10
     reserve
    0.09
     supplies
    0.09
    pletion
    0.09
     Stocks
    0.09
     supply
    0.09
    Activations Density 0.163%

    No Known Activations