© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89313
    Prev
    Next
    INDEX
    Explanations

    references to lottery-related fraud or scams

    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
    chwitz
    -0.08
    ysa
    -0.08
    illin
    -0.07
    rego
    -0.07
    pio
    -0.07
     صÙĨع
    -0.06
    entar
    -0.06
    rek
    -0.06
    .uml
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
    getRepository
    0.06
    afi
    0.06
    ikt
    0.06
     procedures
    0.06
     MacBook
    0.06
    weekly
    0.06
     lim
    0.06
    rossover
    0.05
     overlooked
    0.05
     Global
    0.05
    Activations Density 0.006%

    No Known Activations