© 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. 95233
    Prev
    Next
    INDEX
    Explanations

    phrases related to public presentations and exhibitions

    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
     reportedly
    -0.06
     nighttime
    -0.06
    Workbook
    -0.06
    uling
    -0.05
    :NSLocalizedString
    -0.05
    _delegate
    -0.05
     kale
    -0.05
     SAT
    -0.05
     Barr
    -0.05
    ÙĬÙĩ
    -0.05
    POSITIVE LOGITS
     accession
    0.09
     museum
    0.09
     Museum
    0.08
    useum
    0.08
    館
    0.08
    indow
    0.08
    hist
    0.07
    /catalog
    0.07
    ÃĹ↵↵
    0.07
    ãĥ¼ãĥŀ
    0.07
    Activations Density 0.007%

    No Known Activations