© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 40955
    Prev
    Next
    INDEX
    Explanations

    references to improvement, potential, and personal judgments

    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
    ếu
    -0.09
    vably
    -0.08
     hÃłi
    -0.07
    775
    -0.07
    .Scheme
    -0.07
     باب
    -0.07
    à¸łà¸²à¸ŀ
    -0.07
    ulle
    -0.07
    neh
    -0.07
    778
    -0.07
    POSITIVE LOGITS
     better
    0.15
     Better
    0.14
    better
    0.12
    Better
    0.12
     besser
    0.10
     mieux
    0.09
     mejores
    0.08
     mejor
    0.08
     melhor
    0.08
     лÑĥÑĩÑĪе
    0.07
    Activations Density 0.052%

    No Known Activations