© 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. 83589
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or concern regarding adverse situations

    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
    æĩ
    -0.06
    ÑĸÑĶ
    -0.06
    obot
    -0.06
    ιÏĩ
    -0.05
     treff
    -0.05
    ensa
    -0.05
    addock
    -0.05
    ë³µ
    -0.05
     terme
    -0.05
    ÙĦع
    -0.05
    POSITIVE LOGITS
    ä¸įåŃĺåľ¨
    0.07
     reality
    0.07
    cea
    0.07
    ombat
    0.07
     hoping
    0.07
    eras
    0.07
    PTION
    0.06
     genie
    0.06
    enco
    0.06
    ignore
    0.06
    Activations Density 0.021%

    No Known Activations