© 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. 1939
    Prev
    Next
    INDEX
    Explanations

    terms related to various branches of law and legal proceedings

    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
    -like
    -0.07
    á
    -0.06
    oria
    -0.06
    ,
    -0.06
    nt
    -0.06
    n
    -0.06
    hlen
    -0.06
    -inspired
    -0.06
    abei
    -0.06
    dt
    -0.05
    POSITIVE LOGITS
    ÑģÑĮого
    0.08
    BaÅŁ
    0.07
    رÙĪت
    0.07
    λιο
    0.07
    ÑĥÑĢн
    0.07
    ãģıãģł
    0.07
    åľ¨çº¿éĺħ读
    0.07
    ÙĥاÙħ
    0.07
     ниже
    0.07
    _DEBUG
    0.07
    Activations Density 0.234%

    No Known Activations