© 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. 121275
    Prev
    Next
    INDEX
    Explanations

    phrases related to inspections and assessments of vehicles or technical equipment

    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
    FormatException
    -0.07
    holm
    -0.06
    -caret
    -0.06
    qv
    -0.06
    Ø®Ùħ
    -0.06
    fet
    -0.06
    éĤ£ç§į
    -0.06
    ispers
    -0.06
    Vtbl
    -0.06
     elit
    -0.06
    POSITIVE LOGITS
    ayet
    0.07
    while
    0.07
    uyên
    0.07
     whilst
    0.07
     оÑĩеÑĢед
    0.07
     Äijiá»ĥn
    0.07
     another
    0.07
     demonstrating
    0.06
    ãģªãģĮãĤī
    0.06
    erece
    0.06
    Activations Density 0.023%

    No Known Activations