© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87982
    Prev
    Next
    INDEX
    Explanations

    references to influential female figures in culinary history

    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
     Brew
    -0.08
    fty
    -0.07
     brew
    -0.07
     khung
    -0.06
    _cov
    -0.06
     brewed
    -0.06
    rov
    -0.06
     thirsty
    -0.06
    rego
    -0.06
    ë§IJ
    -0.06
    POSITIVE LOGITS
     food
    0.12
     Food
    0.10
    Food
    0.10
     ingredient
    0.10
    food
    0.10
    -food
    0.09
     kitchens
    0.09
     FOOD
    0.09
     cooking
    0.09
     culinary
    0.09
    Activations Density 0.163%

    No Known Activations