© 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. 87511
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shrug" or variations of it, particularly in contexts of dismissal or indifference

    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
    isu
    -0.08
    egr
    -0.07
    iyle
    -0.07
    ernen
    -0.07
    /op
    -0.07
    ansa
    -0.07
    eam
    -0.07
    enen
    -0.07
    legg
    -0.07
    eum
    -0.07
    POSITIVE LOGITS
     shoulders
    0.09
    orelease
    0.07
     shrugged
    0.06
    leich
    0.06
    iao
    0.06
    stakes
    0.06
    ansk
    0.06
    udget
    0.06
     Shr
    0.06
     commercial
    0.06
    Activations Density 0.002%

    No Known Activations