© 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. 56620
    Prev
    Next
    INDEX
    Explanations

    information related to weather and temperature conditions

    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
    ensen
    -0.07
    ocrine
    -0.06
    izzo
    -0.06
    лÑĥÑĪ
    -0.06
    ivial
    -0.06
     Cul
    -0.06
    è¼Ŀ
    -0.06
    _inline
    -0.06
    allon
    -0.06
    çłĤ
    -0.06
    POSITIVE LOGITS
     temperatures
    0.14
     temperature
    0.12
    temperature
    0.11
     Temperature
    0.10
    Temperature
    0.10
     ÑĤемпеÑĢаÑĤÑĥÑĢа
    0.09
    .temperature
    0.09
     temperatura
    0.09
     Temper
    0.09
     temper
    0.09
    Activations Density 0.023%

    No Known Activations