© 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 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. 57374
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to patent claims and judicial review standards

    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
    etÃŃ
    -0.08
    etleri
    -0.07
    iscrim
    -0.07
    /LICENSE
    -0.07
    -Clause
    -0.07
    arası
    -0.07
    esiz
    -0.06
    flashdata
    -0.06
    icit
    -0.06
    reta
    -0.06
    POSITIVE LOGITS
     defer
    0.09
     review
    0.08
    review
    0.08
    Review
    0.08
     Review
    0.07
     reviewing
    0.07
    defer
    0.07
     REVIEW
    0.07
    gia
    0.06
    _reviews
    0.06
    Activations Density 0.021%

    No Known Activations