© 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 EvalsExportsAPI 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. 128933
    Prev
    Next
    INDEX
    Explanations

    entities related to legal matters and government officials

    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
     Illinois
    -0.08
     Hond
    -0.08
     Chicago
    -0.07
     Budapest
    -0.07
     Utt
    -0.07
    лÑĸв
    -0.07
    Chicago
    -0.07
     Stamford
    -0.07
    _Statics
    -0.07
    usto
    -0.07
    POSITIVE LOGITS
     Plymouth
    0.13
     Baton
    0.09
     Hampshire
    0.08
    PLY
    0.08
     Monaco
    0.08
     mushroom
    0.07
     Mushroom
    0.07
    reactstrap
    0.07
     Lafayette
    0.07
     Prescott
    0.07
    Activations Density 0.234%

    No Known Activations