© 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. 84945
    Prev
    Next
    INDEX
    Explanations

    references to legal processes and the need for legislative changes

    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
    haar
    -0.07
    /tos
    -0.07
    726
    -0.07
     kalk
    -0.06
    atar
    -0.06
    acho
    -0.06
     lif
    -0.06
    üml
    -0.06
    /cop
    -0.06
    /sidebar
    -0.06
    POSITIVE LOGITS
     LEG
    0.07
    leg
    0.07
     legislation
    0.07
    LEG
    0.07
     Congress
    0.07
    iou
    0.07
    bbe
    0.07
     House
    0.07
     legisl
    0.07
     Leg
    0.07
    Activations Density 0.031%

    No Known Activations