© 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. 58024
    Prev
    Next
    INDEX
    Explanations

    references to food and culinary experiences

    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
    ptal
    -0.08
    edla
    -0.07
    евеÑĢ
    -0.07
    инов
    -0.07
    olland
    -0.07
    ilon
    -0.07
    iez
    -0.07
    à¹Ħร
    -0.07
    iec
    -0.07
    ãĥĸãĥ«
    -0.07
    POSITIVE LOGITS
     chips
    0.08
     imag
    0.07
    tings
    0.06
     others
    0.06
     tail
    0.06
     Chips
    0.06
     fate
    0.06
    tu
    0.06
    ting
    0.06
    750
    0.06
    Activations Density 0.009%

    No Known Activations