© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121474
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements, standards, and requirements in documents

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    unately
    -0.09
    iali
    -0.07
    sponsor
    -0.07
    _va
    -0.07
    ech
    -0.07
    ÑģÑĤÑĢÑĥ
    -0.07
    //{{
    -0.07
    ymes
    -0.06
    roken
    -0.06
    ruz
    -0.06
    POSITIVE LOGITS
     hereby
    0.08
     Shall
    0.06
     bind
    0.06
    shall
    0.06
    hee
    0.06
     shall
    0.06
    agal
    0.06
    odcast
    0.06
     mutually
    0.06
    ACK
    0.06
    Activations Density 0.017%

    No Known Activations