© 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. 128391
    Prev
    Next
    INDEX
    Explanations

    descriptive features of real estate properties

    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
    //{{
    -0.08
    furt
    -0.07
    otas
    -0.06
    AGMA
    -0.06
    kker
    -0.06
    icago
    -0.06
    iaz
    -0.05
    izon
    -0.05
    ouri
    -0.05
    esti
    -0.05
    POSITIVE LOGITS
     dbl
    0.08
     адже
    0.07
    antage
    0.07
    spa
    0.07
     UIStoryboard
    0.07
    -fetch
    0.07
    _hooks
    0.07
    úsqueda
    0.07
    idar
    0.06
    æ´»
    0.06
    Activations Density 0.078%

    No Known Activations