© 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. 5090
    Prev
    Next
    INDEX
    Explanations

    references to legal and bureaucratic terminology related to notices and clauses

    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
    ØŃÙħ
    -0.06
    vely
    -0.06
    514
    -0.06
    erals
    -0.06
    997
    -0.06
    ÑĢап
    -0.06
    isson
    -0.06
    каÑĢ
    -0.06
    .disk
    -0.06
    283
    -0.05
    POSITIVE LOGITS
     notice
    0.08
    éĢĢåĩº
    0.08
    notice
    0.07
    лÑİб
    0.07
     quitting
    0.07
     termination
    0.07
     withdraw
    0.07
     withdrawal
    0.07
     quit
    0.07
     Withdraw
    0.07
    Activations Density 0.084%

    No Known Activations