© 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 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. 3465
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to food storage and preparation

    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
     Laundry
    -0.07
     Associated
    -0.06
    ogo
    -0.06
     solic
    -0.06
    forums
    -0.06
    ÑĥÑĤи
    -0.06
     laundry
    -0.05
     Late
    -0.05
     Franken
    -0.05
    éo
    -0.05
    POSITIVE LOGITS
     storing
    0.10
     store
    0.09
     stored
    0.09
     refriger
    0.09
     Store
    0.09
    Stored
    0.08
     storage
    0.08
     Stored
    0.08
    STORE
    0.08
    stored
    0.08
    Activations Density 0.016%

    No Known Activations