© 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. 59860
    Prev
    Next
    INDEX
    Explanations

    references to violence and abuse against vulnerable populations

    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
     thuis
    -0.06
    aters
    -0.06
    ollen
    -0.06
    OOSE
    -0.06
    nnen
    -0.06
    arks
    -0.06
    éĢĢ
    -0.06
     Cord
    -0.06
     stockings
    -0.06
     Shr
    -0.06
    POSITIVE LOGITS
    ulumi
    0.07
     camp
    0.07
     EU
    0.07
     Animalia
    0.07
    ilib
    0.06
     dou
    0.06
    acman
    0.06
    à¸Ĭาย
    0.06
     Morrison
    0.06
     Herman
    0.06
    Activations Density 0.009%

    No Known Activations