© 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. 95262
    Prev
    Next
    INDEX
    Explanations

    numerical data related to percentages and quantities in a manufacturing 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
    agi
    -0.07
    PathComponent
    -0.06
    onus
    -0.06
    ingham
    -0.06
    bourg
    -0.06
    agem
    -0.06
    òng
    -0.06
     trending
    -0.06
    ASA
    -0.06
    ÙĤاء
    -0.05
    POSITIVE LOGITS
    attice
    0.07
     è±
    0.06
    è±
    0.06
    æĬķ
    0.06
    utan
    0.06
    ãĤ¿ãĥ³
    0.06
     Merk
    0.06
    æª
    0.06
    arn
    0.06
    ÏĦολ
    0.06
    Activations Density 0.006%

    No Known Activations