© 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. 41347
    Prev
    Next
    INDEX
    Explanations

    elements related to conflict and violence

    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
     usted
    -0.06
    ãĤ
    -0.06
    udence
    -0.06
    assen
    -0.06
    ëıĻìķĪ
    -0.05
     FI
    -0.05
    friends
    -0.05
    layıcı
    -0.05
    ÑĢÑĸÑĩ
    -0.05
     eyed
    -0.05
    POSITIVE LOGITS
     May
    0.08
     July
    0.08
     February
    0.08
    StackNavigator
    0.07
     addCriterion
    0.07
    aru
    0.07
    .scalablytyped
    0.07
     June
    0.07
    zell
    0.07
     January
    0.07
    Activations Density 0.017%

    No Known Activations