© 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. 92332
    Prev
    Next
    INDEX
    Explanations

    terms related to critical evaluation, particularly in the context of artistic works and their reception

    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
    aign
    -0.07
    ey
    -0.07
    echa
    -0.07
    ÏĥÏĦά
    -0.07
    echn
    -0.07
    567
    -0.06
     Nationals
    -0.06
     eldre
    -0.06
    :async
    -0.06
    .retry
    -0.06
    POSITIVE LOGITS
     favor
    0.06
    .djangoproject
    0.06
    izes
    0.06
     guarded
    0.06
    ided
    0.06
    -guard
    0.06
    ple
    0.06
    CRT
    0.06
     favorable
    0.06
    ands
    0.05
    Activations Density 0.003%

    No Known Activations