© 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. 60532
    Prev
    Next
    INDEX
    Explanations

    themes of moral conviction and commitment to a cause

    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
    liš
    -0.06
    365
    -0.06
    DataProvider
    -0.06
     Abd
    -0.06
    asy
    -0.06
    osaur
    -0.06
    ingen
    -0.06
    NA
    -0.06
    ä¾Ľ
    -0.06
    _threshold
    -0.05
    POSITIVE LOGITS
     cause
    0.08
     progress
    0.08
     science
    0.08
     causes
    0.08
     advancing
    0.08
     advancement
    0.08
     spreading
    0.08
     Cause
    0.08
     ideals
    0.07
    emento
    0.07
    Activations Density 0.063%

    No Known Activations