© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39435
    Prev
    Next
    INDEX
    Explanations

    economic indicators related to housing prices and sales

    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
    ady
    -0.06
     circ
    -0.06
     free
    -0.06
     Mechan
    -0.05
     Physical
    -0.05
     run
    -0.05
     camps
    -0.05
     ÐłÐ¾Ð´
    -0.05
     towards
    -0.05
    heim
    -0.05
    POSITIVE LOGITS
    Median
    0.09
    median
    0.09
     price
    0.09
    -price
    0.08
    Ð¡Ðł
    0.08
     median
    0.08
    edian
    0.08
    prices
    0.08
    æĪ¿
    0.08
    price
    0.08
    Activations Density 0.005%

    No Known Activations