© 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. 120196
    Prev
    Next
    INDEX
    Explanations

    terms related to legal definitions and processes involving juvenile courts

    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
     Nex
    -0.07
    ÙĩÙĪرÛĮ
    -0.07
    alamat
    -0.06
     getTitle
    -0.06
    arb
    -0.06
    aida
    -0.06
     prosecuting
    -0.06
    اتر
    -0.06
    ammen
    -0.06
     claims
    -0.06
    POSITIVE LOGITS
    æŁĦ
    0.07
     shall
    0.07
    _references
    0.06
     Shall
    0.06
     Placement
    0.06
     Counties
    0.06
    룰
    0.06
    باÙĨ
    0.06
    _tickets
    0.06
    à¤Łà¤°
    0.06
    Activations Density 0.005%

    No Known Activations