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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72942
    Prev
    Next
    INDEX
    Explanations

    numbers related to casualties and injuries in violent events

    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
     zby
    -0.08
    antine
    -0.08
    Ø®ÙĪاÙĨ
    -0.08
    vise
    -0.08
    soever
    -0.08
    udden
    -0.07
    velle
    -0.07
    elon
    -0.07
    yor
    -0.07
    idlo
    -0.07
    POSITIVE LOGITS
     people
    0.08
     dead
    0.06
     person
    0.06
     staff
    0.06
     adult
    0.06
     everyone
    0.06
    0.05
     man
    0.05
     worker
    0.05
     child
    0.05
    Activations Density 0.018%

    No Known Activations