© 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. 4219
    Prev
    Next
    INDEX
    Explanations

    intensifiers or adverbs indicating strong emphasis or quality

    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
    anus
    -0.06
     Perry
    -0.06
    /std
    -0.06
    unifu
    -0.06
    etty
    -0.06
     Priority
    -0.06
    asley
    -0.06
     allegedly
    -0.06
    obot
    -0.06
    нии
    -0.06
    POSITIVE LOGITS
    .Compute
    0.07
    živ
    0.07
    ritz
    0.07
    Į¨
    0.06
    Suite
    0.06
    ĽĪ
    0.06
    é¾Ħ
    0.06
    ÏĥοÏħ
    0.06
    DCF
    0.06
    dzi
    0.06
    Activations Density 0.062%

    No Known Activations