© 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. 58981
    Prev
    Next
    INDEX
    Explanations

    references to gambling and gaming terminology

    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
    omon
    -0.07
    ect
    -0.07
    iza
    -0.07
    hatt
    -0.07
    613
    -0.07
    ervers
    -0.06
    lou
    -0.06
    l
    -0.06
     Fur
    -0.06
    -sh
    -0.06
    POSITIVE LOGITS
    .dsl
    0.08
    _exempt
    0.07
    AVE
    0.07
    AGMA
    0.07
    γκα
    0.07
    empo
    0.07
    aleb
    0.07
    .son
    0.07
     Infragistics
    0.07
    utsch
    0.07
    Activations Density 0.008%

    No Known Activations