© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40122
    Prev
    Next
    INDEX
    Explanations

    words related to subtle discomfort or irritation

    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
    ouz
    -0.07
    ukkit
    -0.07
    airy
    -0.07
    imdi
    -0.06
    ogne
    -0.06
     mouth
    -0.06
    éĿ¢çļĦ
    -0.06
    åı£
    -0.06
    idi
    -0.06
    arde
    -0.06
    POSITIVE LOGITS
     conscience
    0.08
    ingly
    0.08
    ette
    0.07
    ling
    0.07
    .wx
    0.06
    ovit
    0.06
     SOS
    0.06
     зÑĢениÑı
    0.06
    chers
    0.06
    åĦ¿
    0.06
    Activations Density 0.021%

    No Known Activations