© 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. 81439
    Prev
    Next
    INDEX
    Explanations

    references to comparative legal cases and legal principles

    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
    ami
    -0.08
    оÑĥ
    -0.08
    AMI
    -0.07
    лÑĥÑĩ
    -0.07
     Voc
    -0.07
    coni
    -0.07
    ogle
    -0.07
    .jdesktop
    -0.07
    jeme
    -0.07
    δÏģα
    -0.06
    POSITIVE LOGITS
     Advantage
    0.08
     analysis
    0.08
     advantage
    0.08
    isons
    0.07
     disadvantage
    0.07
     approach
    0.07
     wash
    0.07
    âķĹ
    0.07
     law
    0.07
     across
    0.06
    Activations Density 0.005%

    No Known Activations