© 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. 118303
    Prev
    Next
    INDEX
    Explanations

    connections between historical political movements and their impacts

    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
    taÅŁ
    -0.08
    رÛĮاÙĨ
    -0.08
    /gtest
    -0.08
    onomous
    -0.08
    byname
    -0.08
     demokrat
    -0.08
    ertainment
    -0.08
    OKIE
    -0.08
    Uvs
    -0.08
     fisse
    -0.07
    POSITIVE LOGITS
     trans
    0.07
    Ìģ
    0.07
     reception
    0.06
    umo
    0.06
     East
    0.06
     between
    0.06
     post
    0.06
     Fate
    0.06
    Ì
    0.06
     Fed
    0.06
    Activations Density 0.002%

    No Known Activations