© 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. 39762
    Prev
    Next
    INDEX
    Explanations

    words that indicate contrast or exception within contexts

    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
     maybe
    -0.07
    bÃŃr
    -0.07
     Plus
    -0.06
    odon
    -0.06
     miss
    -0.06
    acha
    -0.06
    ÑĥÑĢа
    -0.06
     ought
    -0.06
    ivi
    -0.05
    Ñĥл
    -0.05
    POSITIVE LOGITS
     recent
    0.08
    ertain
    0.08
    iew
    0.07
    ãģªãģĮ
    0.07
    oped
    0.07
    anel
    0.07
    olders
    0.07
    burgh
    0.07
    ÙĤد
    0.07
     lately
    0.07
    Activations Density 0.032%

    No Known Activations