© 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. 5084
    Prev
    Next
    INDEX
    Explanations

    references to bureaucratic processes related to marriage registration

    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
     Afghan
    -0.09
     Kolkata
    -0.08
    Atlanta
    -0.07
     Ahmet
    -0.07
    èį
    -0.07
     Atlanta
    -0.07
    enthal
    -0.07
     Kabul
    -0.07
    Ill
    -0.07
     Kansas
    -0.07
    POSITIVE LOGITS
     Oman
    0.13
     Bahrain
    0.10
     Portland
    0.10
    Portland
    0.09
     Gulf
    0.09
     Jeb
    0.08
     Kingdom
    0.07
     Fey
    0.07
     Al
    0.07
     Tucson
    0.07
    Activations Density 0.008%

    No Known Activations