© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88583
    Prev
    Next
    INDEX
    Explanations

    concepts related to energy access and medical logistics

    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
     launder
    -0.06
     grown
    -0.06
     sol
    -0.06
     hid
    -0.05
     Tee
    -0.05
    522
    -0.05
     Nav
    -0.05
    609
    -0.05
    623
    -0.05
    411
    -0.05
    POSITIVE LOGITS
     temperature
    0.13
     Temperature
    0.12
     temperatures
    0.11
    temperature
    0.11
    Temperature
    0.10
     temperatura
    0.10
    温度
    0.10
     chilling
    0.09
    -storage
    0.09
     refriger
    0.09
    Activations Density 0.038%

    No Known Activations