© 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. 93417
    Prev
    Next
    INDEX
    Explanations

    terms related to culinary topics and cuisine

    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
    portlet
    -0.07
    odore
    -0.07
    rego
    -0.07
    itur
    -0.07
    eless
    -0.07
    cheng
    -0.07
    izio
    -0.07
    окол
    -0.07
    infeld
    -0.07
    avier
    -0.07
    POSITIVE LOGITS
     Morton
    0.06
    ette
    0.06
    inary
    0.06
    mn
    0.06
    /icons
    0.06
    PAD
    0.06
     Brennan
    0.05
     recherche
    0.05
    /colors
    0.05
     ê²ĥëıĦ
    0.05
    Activations Density 0.005%

    No Known Activations