© 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 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. 93845
    Prev
    Next
    INDEX
    Explanations

    references to law firms and their partners or associates

    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
    radu
    -0.07
    оваÑĢи
    -0.07
    -caret
    -0.07
    .jsoup
    -0.07
    hlen
    -0.07
     provoz
    -0.07
     æĺ
    -0.07
    adol
    -0.07
    ozem
    -0.06
    upert
    -0.06
    POSITIVE LOGITS
     &
    0.09
     Associates
    0.09
     attorneys
    0.08
     LLP
    0.08
     attorney
    0.08
    att
    0.07
     firm
    0.07
     associates
    0.07
     +
    0.07
    izer
    0.07
    Activations Density 0.043%

    No Known Activations