© 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. 87018
    Prev
    Next
    INDEX
    Explanations

    terms related to real estate transactions and agreements

    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
    bourg
    -0.10
    ÅĻeh
    -0.08
    chwitz
    -0.08
    ahun
    -0.08
    оÑģÑĥд
    -0.08
    avl
    -0.08
    aleigh
    -0.07
    ÑĸдÑĥ
    -0.07
     dök
    -0.07
     nues
    -0.07
    POSITIVE LOGITS
     agreed
    0.07
    ovel
    0.07
     agreement
    0.07
     agreeing
    0.06
     Agreement
    0.06
     transfer
    0.06
     esc
    0.06
     struct
    0.06
     intermediate
    0.06
     arrangement
    0.06
    Activations Density 0.003%

    No Known Activations