© 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. 15349
    Prev
    Next
    INDEX
    Explanations

    terms related to art and its organizational structures, especially concerning exhibitions and curators

    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
    anova
    -0.06
     Journalism
    -0.06
    rzy
    -0.06
    LayoutConstraint
    -0.06
    ogl
    -0.06
    oyer
    -0.06
     Kick
    -0.06
    kowski
    -0.06
    Į¨
    -0.06
     íĻĶ
    -0.06
    POSITIVE LOGITS
     museum
    0.13
     Museum
    0.11
     curator
    0.11
     museums
    0.10
    useum
    0.10
     muse
    0.09
    åįļçī©
    0.08
     Muse
    0.08
     мÑĥз
    0.08
     çŃ
    0.08
    Activations Density 0.023%

    No Known Activations