© 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. 5-LLAMASCOPE-RES-131K
    11. 125410
    Prev
    Next
    INDEX
    Explanations

    terms related to microwave heating processes and the operation of microwave ovens

    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
    dera
    -0.07
     Nin
    -0.05
    611
    -0.05
     OnCollision
    -0.05
    yun
    -0.05
    ucle
    -0.05
    atat
    -0.05
    SG
    -0.05
    oten
    -0.05
    ook
    -0.05
    POSITIVE LOGITS
    ÑĢива
    0.08
    physics
    0.07
    enga
    0.06
    .tc
    0.06
    ailer
    0.06
    ocolate
    0.06
    ARRIER
    0.06
    ntag
    0.06
    CTX
    0.06
    <context
    0.06
    Activations Density 0.070%

    No Known Activations