© 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 EvalsExportsinterp-engineNEWAPI 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. 95105
    Prev
    Next
    INDEX
    Explanations

    expressions related to cooking 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
    ihan
    -0.07
    kees
    -0.07
    swer
    -0.06
    late
    -0.06
    vo
    -0.06
    .slim
    -0.06
    rž
    -0.06
     RuntimeObject
    -0.06
    å¯
    -0.06
     caffe
    -0.06
    POSITIVE LOGITS
     cooking
    0.09
     Cooking
    0.09
     cook
    0.08
     cooks
    0.07
    orr
    0.07
    Cook
    0.07
     skills
    0.07
     recipes
    0.06
    çĥ
    0.06
     Household
    0.06
    Activations Density 0.015%

    No Known Activations