© 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. 15-LLAMASCOPE-RES-131K
    11. 62452
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and judicial processes

    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
    ighbor
    -0.07
    ittel
    -0.07
    جÛĮ
    -0.06
    çħ
    -0.06
    stride
    -0.06
    اجع
    -0.06
    ÑĦеÑĢ
    -0.06
    ensi
    -0.06
    (dtype
    -0.06
    acie
    -0.06
    POSITIVE LOGITS
     cases
    0.08
    cases
    0.06
    unger
    0.06
    ng
    0.06
    oba
    0.06
     case
    0.06
    prus
    0.06
    _Resource
    0.06
    itis
    0.06
    ertos
    0.06
    Activations Density 0.024%

    No Known Activations