© 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. 72189
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and criminal issues

    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
    ivi
    -0.07
     concussion
    -0.07
     TMPro
    -0.07
    ivent
    -0.06
    pill
    -0.06
    acre
    -0.06
    orer
    -0.06
    ãĥĹãĥª
    -0.06
    ald
    -0.06
    ãĥ³ãĥĢ
    -0.06
    POSITIVE LOGITS
     only
    0.06
     entire
    0.06
    Argument
    0.06
     Serial
    0.06
     cop
    0.06
     Clarkson
    0.06
    (Link
    0.06
    ILLISECONDS
    0.05
    -da
    0.05
    0.05
    Activations Density 0.041%

    No Known Activations