© 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. 118329
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of property features in real estate listings

    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
     bottom
    -0.09
    åºķ
    -0.08
    bottom
    -0.08
     Bottom
    -0.08
    Bottom
    -0.07
     bottoms
    -0.07
     BOTTOM
    -0.07
     Zem
    -0.07
    BOTTOM
    -0.07
     below
    -0.06
    POSITIVE LOGITS
    olar
    0.08
    doch
    0.07
     ActiveSupport
    0.06
    ifix
    0.06
    airs
    0.06
    bildung
    0.06
    ÙĨدگاÙĨ
    0.06
     Merchant
    0.06
    aska
    0.06
    _exempt
    0.06
    Activations Density 0.015%

    No Known Activations