© 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. 84933
    Prev
    Next
    INDEX
    Explanations

    details related to violent incidents or crimes

    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
    gua
    -0.07
    tid
    -0.06
    phem
    -0.06
     invade
    -0.06
    競
    -0.06
    andest
    -0.06
    WWW
    -0.06
    Reusable
    -0.06
    sea
    -0.06
     Kramer
    -0.06
    POSITIVE LOGITS
     hostage
    0.09
     Negot
    0.08
     negot
    0.07
     hostages
    0.07
     squat
    0.07
     negotiations
    0.07
     positional
    0.07
     surrender
    0.06
    agrams
    0.06
     resolution
    0.06
    Activations Density 0.012%

    No Known Activations