© 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. 9-LLAMASCOPE-RES-131K
    11. 96283
    Prev
    Next
    INDEX
    Explanations

    technical or coding elements related to user interface components

    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
    kip
    -0.08
    ammen
    -0.07
    dera
    -0.07
    antro
    -0.06
    elmet
    -0.06
    opus
    -0.06
    jer
    -0.06
    pio
    -0.06
     Contents
    -0.06
    edin
    -0.06
    POSITIVE LOGITS
    :///
    0.08
     Kosten
    0.07
    سÙĪب
    0.07
    iken
    0.07
     kiá»ĥu
    0.07
     Roose
    0.06
    еÑı
    0.06
    Äįel
    0.06
     nghá»ģ
    0.06
    Ãłnh
    0.06
    Activations Density 0.004%

    No Known Activations