© 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. 57313
    Prev
    Next
    INDEX
    Explanations

    cooking and preparation instructions related to food

    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
    amble
    -0.07
    erten
    -0.07
    asil
    -0.06
    otron
    -0.06
    oux
    -0.06
    unner
    -0.06
    akan
    -0.06
    holm
    -0.06
    urgeon
    -0.06
     znam
    -0.06
    POSITIVE LOGITS
    転
    0.07
    hou
    0.06
    Ķ
    0.06
    á»iji
    0.06
    care
    0.06
    byname
    0.06
    uent
    0.06
    orda
    0.06
    ObjectContext
    0.06
    ĩ
    0.06
    Activations Density 0.009%

    No Known Activations