© 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. 106642
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional or physical discomfort

    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
    ardu
    -0.08
    hiba
    -0.08
    andest
    -0.08
    ¦y
    -0.08
    ongyang
    -0.08
    DebugEnabled
    -0.08
    ¶ģ
    -0.07
    ichern
    -0.07
    (æľ¨
    -0.07
    ulumi
    -0.07
    POSITIVE LOGITS
     anywhere
    0.06
     lump
    0.06
    ig
    0.06
    ICS
    0.06
    ate
    0.06
    âĢ
    0.06
     Rox
    0.06
     Shak
    0.05
    it
    0.05
     pic
    0.05
    Activations Density 0.001%

    No Known Activations