© 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. 5099
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking and food preparation techniques

    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
    512
    -0.06
    adro
    -0.06
    Padding
    -0.06
     tag
    -0.06
     Fen
    -0.05
    uraa
    -0.05
     veniam
    -0.05
    æľĽ
    -0.05
    ba
    -0.05
    æ
    -0.05
    POSITIVE LOGITS
     Refriger
    0.07
     perish
    0.07
     fres
    0.07
     immedi
    0.07
     immediate
    0.07
    Fresh
    0.07
     immediately
    0.07
     Fresh
    0.07
     refriger
    0.07
    within
    0.07
    Activations Density 0.024%

    No Known Activations