© 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. 15-LLAMASCOPE-RES-131K
    11. 88890
    Prev
    Next
    INDEX
    Explanations

    terms related to state connections or relationships in a geographical context

    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
     Jungle
    -0.06
     Ridley
    -0.06
    ica
    -0.06
    âĢ¦↵
    -0.06
    μÏĢο
    -0.05
    á»įt
    -0.05
     Danger
    -0.05
    iminal
    -0.05
    vation
    -0.05
    ena
    -0.05
    POSITIVE LOGITS
     اÙĦÙħتØŃدة
    0.09
     ÙħتØŃدÙĩ
    0.08
    pton
    0.08
    minor
    0.07
    imas
    0.07
     Unidos
    0.07
     Ø¢ÙħرÛĮکا
    0.07
    Latch
    0.07
     Minor
    0.07
    .observable
    0.07
    Activations Density 0.030%

    No Known Activations