© 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. 105596
    Prev
    Next
    INDEX
    Explanations

    positive emotional descriptors and expressions of admiration or enjoyment

    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
     enough
    -0.08
    olib
    -0.07
     more
    -0.06
     somewhat
    -0.06
    ordo
    -0.06
    ater
    -0.06
    zel
    -0.06
     ,
    -0.06
     or
    -0.06
    oret
    -0.06
    POSITIVE LOGITS
    oted
    0.07
    @nate
    0.07
    APO
    0.07
     noreferrer
    0.07
    hatt
    0.07
    %č↵
    0.07
    -LAST
    0.07
    InnerText
    0.07
    616
    0.07
     dziew
    0.07
    Activations Density 0.043%

    No Known Activations