© 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. 15697
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to the process of marriage registration and legal documentation

    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
    agh
    -0.07
    ince
    -0.07
    iedo
    -0.07
     æĬķ稿
    -0.07
    annonce
    -0.06
    ä»°
    -0.06
    æķĻå¸Ī
    -0.06
    ourke
    -0.06
    vr
    -0.06
    coder
    -0.06
    POSITIVE LOGITS
     Fukushima
    0.07
    imar
    0.06
     old
    0.06
     Old
    0.06
     visits
    0.06
    λη
    0.06
    quet
    0.06
     fees
    0.06
    Raster
    0.06
    vely
    0.06
    Activations Density 0.014%

    No Known Activations