© 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 EvalsExportsinterp-engineNEWAPI 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. 31148
    Prev
    Next
    INDEX
    Explanations

    concepts related to government policies and their effects

    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
    damn
    -0.07
    ltra
    -0.07
    inho
    -0.07
    oriously
    -0.07
     åĪ
    -0.07
    zl
    -0.07
    weis
    -0.07
    ikt
    -0.07
     nhau
    -0.07
    evi
    -0.07
    POSITIVE LOGITS
     being
    0.08
     has
    0.07
     could
    0.07
     will
    0.06
    being
    0.06
     are
    0.06
    ih
    0.06
     Pruitt
    0.06
    lee
    0.06
    é¡»
    0.05
    Activations Density 0.102%

    No Known Activations