© 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. 128362
    Prev
    Next
    INDEX
    Explanations

    statistics and data related to religious demographics and activities

    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
    å±¥
    -0.06
     nackte
    -0.06
    olis
    -0.06
    [..
    -0.06
     Katz
    -0.06
    621
    -0.06
     Municipal
    -0.06
     coalition
    -0.06
    .AutoSizeMode
    -0.06
     Goodman
    -0.06
    POSITIVE LOGITS
    евиÑĩ
    0.07
     Worldwide
    0.07
     Smy
    0.07
    adden
    0.07
     doctr
    0.07
    etting
    0.06
    ÑĮко
    0.06
    alue
    0.06
    Pacific
    0.06
     رسÙħ
    0.06
    Activations Density 0.000%

    No Known Activations