© 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. 5-LLAMASCOPE-RES-131K
    11. 125597
    Prev
    Next
    INDEX
    Explanations

    temperature-related terms and descriptions of cold weather phenomena

    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
     incom
    -0.07
    bare
    -0.07
    SHARE
    -0.06
    kov
    -0.06
    rant
    -0.06
    á»Ļ
    -0.06
    asa
    -0.06
    hall
    -0.06
    MOOTH
    -0.06
     barg
    -0.06
    POSITIVE LOGITS
    Credits
    0.07
    cape
    0.07
     Credits
    0.07
    otton
    0.07
    arris
    0.07
    nar
    0.06
    obot
    0.06
    оÑıн
    0.06
    ordes
    0.06
    è¯Ŀ
    0.06
    Activations Density 0.014%

    No Known Activations