© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118358
    Prev
    Next
    INDEX
    Explanations

    words related to cooking and ingredient 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
    ange
    -0.06
    znik
    -0.06
    manda
    -0.06
    OPTIONS
    -0.06
    aries
    -0.06
    lic
    -0.06
    adu
    -0.06
    лава
    -0.06
     League
    -0.06
    pto
    -0.06
    POSITIVE LOGITS
    imler
    0.07
    ]|[
    0.07
    AREST
    0.06
    ä¸įåIJĮçļĦ
    0.06
    æŀ¶
    0.06
    emez
    0.06
    CodeGen
    0.06
    atego
    0.06
    hod
    0.06
    çļĦæĺ¯
    0.06
    Activations Density 0.020%

    No Known Activations