© 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 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. 78444
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emotional tension or personal conflict

    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
    èĥŀ
    -0.07
    yt
    -0.07
    edis
    -0.07
    æŃ©
    -0.07
    ogui
    -0.07
    antz
    -0.07
    undry
    -0.07
     eldre
    -0.07
    utex
    -0.07
    unday
    -0.07
    POSITIVE LOGITS
     withholding
    0.06
     Meanwhile
    0.06
     learns
    0.05
    opers
    0.05
     Their
    0.05
    avel
    0.05
     discovers
    0.05
     Specs
    0.05
     um
    0.05
    vy
    0.05
    Activations Density 0.019%

    No Known Activations