© 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. 69526
    Prev
    Next
    INDEX
    Explanations

    references to renovations or transformations of buildings and monuments

    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
    ãĥ¼ãĥĭ
    -0.07
    ÑĢÑĸÑĩ
    -0.06
    oupon
    -0.06
     feeder
    -0.06
    ÑĢон
    -0.06
    ɵ
    -0.06
    íıŃ
    -0.06
     eros
    -0.06
    unset
    -0.06
    ÙĨب
    -0.06
    POSITIVE LOGITS
     preservation
    0.10
     Preservation
    0.10
     project
    0.09
     restoration
    0.09
     preserve
    0.09
     heritage
    0.08
     restore
    0.08
    .restore
    0.08
     reuse
    0.08
     preserved
    0.08
    Activations Density 0.005%

    No Known Activations