© 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. 55319
    Prev
    Next
    INDEX
    Explanations

    topics related to discussing personal experiences and history

    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
    à¥ĭà¤ķर
    -0.08
    pyx
    -0.07
    à¥ģह
    -0.07
    رÛĮب
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    EMPL
    -0.07
    utar
    -0.07
    inç
    -0.07
    åŀ
    -0.06
    à¥įà¤Ĺत
    -0.06
    POSITIVE LOGITS
    751
    0.07
     sensitive
    0.07
     topics
    0.07
    989
    0.07
     topic
    0.07
    990
    0.06
     matters
    0.06
    690
    0.06
     religion
    0.06
     past
    0.06
    Activations Density 0.025%

    No Known Activations