© 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. 22-LLAMASCOPE-RES-131K
    11. 3859
    Prev
    Next
    INDEX
    Explanations

    references to incidents of sexual violence and their victims

    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
    éŁ¿
    -0.08
    asl
    -0.07
     sân
    -0.07
    morgan
    -0.07
    contres
    -0.07
    addock
    -0.07
     murdering
    -0.07
    .decorate
    -0.07
    ancode
    -0.07
    ali
    -0.07
    POSITIVE LOGITS
     kid
    0.07
     left
    0.07
     attacked
    0.07
     subjected
    0.07
     beaten
    0.07
     subject
    0.07
     beat
    0.06
     forced
    0.06
     twice
    0.06
    atars
    0.06
    Activations Density 0.022%

    No Known Activations