© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 58967
    Prev
    Next
    INDEX
    Explanations

    terms related to recipes and culinary ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Recipe titles, section headings, and ingredient lists in a burger cookbook, typically appearing at the beginning of recipe sections or in directory/index listings.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    aign
    -0.07
     Uhr
    -0.06
    onde
    -0.06
    grave
    -0.06
    agne
    -0.06
     Beste
    -0.06
    ablo
    -0.06
    맹
    -0.06
    iyas
    -0.06
    Ñıн
    -0.06
    POSITIVE LOGITS
    ftware
    0.08
     consenting
    0.06
    ackers
    0.06
    ãģ¦
    0.06
    ÄĽt
    0.06
    atori
    0.06
    ly
    0.06
    inne
    0.06
    427
    0.06
    iate
    0.06
    Activations Density 0.064%

    No Known Activations