© 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. 30898
    Prev
    Next
    INDEX
    Explanations

    elements related to legal documents and their structure

    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
    SPARENT
    -0.08
    irc
    -0.07
     ÐľÐµÑģÑĤо
    -0.06
    eer
    -0.06
    寸
    -0.06
    azu
    -0.06
    urd
    -0.06
    太
    -0.06
    -League
    -0.06
    .variant
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.07
    ù
    0.07
     III
    0.06
     Mystic
    0.06
    ãĥ¼ãĥį
    0.06
    oya
    0.06
     part
    0.06
     prelim
    0.06
     autos
    0.06
     II
    0.06
    Activations Density 0.019%

    No Known Activations