© 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. 86118
    Prev
    Next
    INDEX
    Explanations

    terms related to participants and actions in legal contexts

    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
    anical
    -0.07
    licer
    -0.07
    illet
    -0.07
    yer
    -0.07
    ATAB
    -0.07
    brid
    -0.07
    ırak
    -0.06
     proverb
    -0.06
    rray
    -0.06
    uelle
    -0.06
    POSITIVE LOGITS
    nd
    0.07
    atrix
    0.07
    able
    0.06
    mes
    0.06
    ers
    0.06
    iec
    0.06
    inker
    0.06
    Matrix
    0.06
    UTDOWN
    0.06
    ounds
    0.06
    Activations Density 0.001%

    No Known Activations