© 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. 82394
    Prev
    Next
    INDEX
    Explanations

    expressions of frustration or impatience

    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
    utenberg
    -0.07
    uci
    -0.07
    adies
    -0.07
    pa
    -0.06
    æŀIJ
    -0.06
    pause
    -0.06
    æ³£
    -0.06
     Å¡iro
    -0.06
    ypi
    -0.06
    ERIC
    -0.06
    POSITIVE LOGITS
     impatient
    0.12
     annoyance
    0.11
     irritation
    0.10
     annoyed
    0.10
     frustration
    0.09
     irrit
    0.09
     irritated
    0.08
     resent
    0.08
     frustrated
    0.08
     frustrations
    0.08
    Activations Density 0.044%

    No Known Activations