© 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. 17-LLAMASCOPE-RES-131K
    11. 15906
    Prev
    Next
    INDEX
    Explanations

    references to energy consumption and billing patterns

    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
    osate
    -0.07
    -gnu
    -0.07
    ertino
    -0.07
    uib
    -0.07
    etti
    -0.06
    esty
    -0.06
    ields
    -0.06
     καλÏį
    -0.06
    iç
    -0.06
    Spo
    -0.06
    POSITIVE LOGITS
     peak
    0.10
    å³°
    0.09
    Peak
    0.08
     Peak
    0.08
    peak
    0.08
    _peak
    0.07
     power
    0.07
     gridColumn
    0.07
     peaks
    0.07
     brush
    0.07
    Activations Density 0.001%

    No Known Activations