© 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. 124832
    Prev
    Next
    INDEX
    Explanations

    mentions of severe weather events, particularly storms and hurricanes

    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
    δÏĮ
    -0.07
    oding
    -0.06
    imb
    -0.06
     Serg
    -0.06
    gor
    -0.06
    openhagen
    -0.06
     Wick
    -0.06
    irm
    -0.06
    anning
    -0.06
    piel
    -0.06
    POSITIVE LOGITS
    ishly
    0.07
    оло
    0.07
    front
    0.07
    arium
    0.07
    æ£ļ
    0.07
    LIKELY
    0.06
    -season
    0.06
    bum
    0.06
    iquer
    0.06
    proof
    0.06
    Activations Density 0.012%

    No Known Activations