© 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. 17-LLAMASCOPE-RES-131K
    11. 15710
    Prev
    Next
    INDEX
    Explanations

    references to tragic events and individuals involved in violence or death, particularly in the context of immigration and crime discussions

    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
    глÑıд
    -0.07
     bankrupt
    -0.07
    anka
    -0.06
    ungan
    -0.06
    lesi
    -0.06
    bab
    -0.06
     selves
    -0.06
     quis
    -0.06
     retire
    -0.06
    ivent
    -0.06
    POSITIVE LOGITS
     memorial
    0.08
     died
    0.07
     Memorial
    0.07
    StateException
    0.07
    case
    0.07
    -case
    0.07
    PointerException
    0.06
     case
    0.06
    éģº
    0.06
     tragedy
    0.06
    Activations Density 0.020%

    No Known Activations