© 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. 15-LLAMASCOPE-RES-131K
    11. 104232
    Prev
    Next
    INDEX
    Explanations

    phrases indicating upward movement or improvement, often related to personal or situational growth

    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
    rez
    -0.07
    apolis
    -0.07
    illon
    -0.07
    ofi
    -0.07
    ullet
    -0.07
    wich
    -0.07
     Dumpster
    -0.07
    ENCHMARK
    -0.07
    ued
    -0.07
    roi
    -0.06
    POSITIVE LOGITS
    /stretch
    0.07
    .mo
    0.06
    ãģĦãģ¦
    0.06
    ulta
    0.06
    ãĥ£
    0.06
    /Peak
    0.06
    odel
    0.06
     Moy
    0.06
     Candle
    0.06
    ivals
    0.06
    Activations Density 0.023%

    No Known Activations