© 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. 105141
    Prev
    Next
    INDEX
    Explanations

    references to judges or judgment within a contextual framework

    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
    .Automation
    -0.08
    ieber
    -0.07
    .MixedReality
    -0.07
    uros
    -0.07
     огÑĢа
    -0.07
    ısıyla
    -0.07
    baÅŁ
    -0.07
     зави
    -0.07
    átek
    -0.07
    OffsetTable
    -0.07
    POSITIVE LOGITS
     activity
    0.07
    ahn
    0.07
     used
    0.07
    æĽ¾
    0.07
     ever
    0.07
     present
    0.06
    بÙĪ
    0.06
     usage
    0.06
     participated
    0.06
    Ah
    0.06
    Activations Density 0.023%

    No Known Activations