© 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. 89671
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal contracts and agreements

    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
    tak
    -0.06
    iesen
    -0.06
    adden
    -0.06
     teh
    -0.06
    dül
    -0.06
    /people
    -0.06
    era
    -0.05
    pson
    -0.05
     Paso
    -0.05
     Pas
    -0.05
    POSITIVE LOGITS
    баÑģ
    0.08
    ãĤ«ãĥ«
    0.07
     Gül
    0.07
    adesh
    0.07
    Äįer
    0.07
    alan
    0.07
    ocop
    0.07
     #=>
    0.06
    erner
    0.06
    indr
    0.06
    Activations Density 0.002%

    No Known Activations