© 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. 28689
    Prev
    Next
    INDEX
    Explanations

    references to casualties and events involving large groups of people in distress

    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
    izzo
    -0.08
     odom
    -0.07
    aad
    -0.06
    adelphia
    -0.06
    aux
    -0.06
    kün
    -0.06
     sond
    -0.06
    -addon
    -0.06
    ivas
    -0.06
    تÙĪر
    -0.06
    POSITIVE LOGITS
    noinspection
    0.07
    aze
    0.07
    æŃ£åľ¨
    0.06
    å¼¹
    0.06
    ÏĨο
    0.06
     vulnerable
    0.06
     moments
    0.06
     inoc
    0.06
    ero
    0.06
     innocent
    0.06
    Activations Density 0.026%

    No Known Activations