© 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. 75063
    Prev
    Next
    INDEX
    Explanations

    references to museum exhibitions and their features

    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
    본
    -0.07
    anka
    -0.07
    ноÑĩ
    -0.06
    skyt
    -0.06
     validationResult
    -0.06
     worry
    -0.06
    annonce
    -0.06
     hass
    -0.06
    åľĴ
    -0.06
    Ú©Ø´
    -0.06
    POSITIVE LOGITS
     displays
    0.07
    -display
    0.07
     exhibit
    0.07
     Museum
    0.07
     exhibits
    0.07
     museum
    0.07
    "display
    0.07
    Displays
    0.07
     galleries
    0.07
    /display
    0.07
    Activations Density 0.016%

    No Known Activations