© 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. 81205
    Prev
    Next
    INDEX
    Explanations

    mentions of museums and their significance

    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
     airports
    -0.06
     isolated
    -0.06
     nud
    -0.06
    itta
    -0.05
     involved
    -0.05
     camp
    -0.05
     extra
    -0.05
     extras
    -0.05
    /Set
    -0.05
     power
    -0.05
    POSITIVE LOGITS
     museum
    0.14
     Museum
    0.13
     museums
    0.12
    useum
    0.12
    collections
    0.11
     collections
    0.10
     muse
    0.10
    åįļçī©
    0.10
     Muse
    0.10
    Collections
    0.09
    Activations Density 0.034%

    No Known Activations