© 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 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. 130241
    Prev
    Next
    INDEX
    Explanations

    references to art donations and loans

    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
    æĵį
    -0.06
     пÑĢавда
    -0.06
    /pdf
    -0.06
    urst
    -0.06
     billig
    -0.06
    omor
    -0.06
     runoff
    -0.06
     anc
    -0.06
     ÐĹам
    -0.06
    ymes
    -0.05
    POSITIVE LOGITS
     donation
    0.09
     museum
    0.09
     gift
    0.09
     accession
    0.09
     acquisitions
    0.09
     acquisition
    0.08
     museums
    0.08
     Museum
    0.08
     Collections
    0.08
     Acquisition
    0.08
    Activations Density 0.003%

    No Known Activations