© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    references to violence and crisis situations

    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
    geme
    -0.07
    à¹īà¸Ńม
    -0.07
    inent
    -0.07
    á»įc
    -0.07
    Insensitive
    -0.07
    steen
    -0.07
    gart
    -0.06
     triplet
    -0.06
     kole
    -0.06
    ạ
    -0.06
    POSITIVE LOGITS
     conflict
    0.09
     political
    0.08
     conflicts
    0.08
     civil
    0.07
     violence
    0.07
     Stability
    0.07
     cas
    0.07
    ç²¾
    0.07
     stability
    0.07
    ucene
    0.06
    Activations Density 0.064%

    No Known Activations