© 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. 15-LLAMASCOPE-RES-131K
    11. 27516
    Prev
    Next
    INDEX
    Explanations

    terms related to cooking techniques and food preparation methods

    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
    gz
    -0.07
    uentes
    -0.06
     <*>
    -0.06
    StringLength
    -0.06
    ksen
    -0.06
    лÑĥг
    -0.06
    atat
    -0.06
    á»IJ
    -0.06
    éħį
    -0.06
    éĽ
    -0.06
    POSITIVE LOGITS
    ened
    0.07
    mitter
    0.07
    edException
    0.07
    æľĭ
    0.06
    /Internal
    0.06
    947
    0.06
    edImage
    0.06
    ounter
    0.06
    155
    0.06
    aus
    0.06
    Activations Density 0.008%

    No Known Activations