© 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. 41389
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and legislative processes

    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
    itsu
    -0.07
    harma
    -0.07
    िष
    -0.06
    _FAULT
    -0.06
    mans
    -0.06
    tering
    -0.06
    verse
    -0.06
    andy
    -0.06
     klu
    -0.06
     Ta
    -0.06
    POSITIVE LOGITS
     accordingly
    0.10
     beyond
    0.07
     Accordingly
    0.07
     away
    0.07
    foy
    0.07
    igi
    0.07
    addock
    0.06
    chet
    0.06
     Rib
    0.06
    496
    0.06
    Activations Density 0.091%

    No Known Activations