© 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. 95762
    Prev
    Next
    INDEX
    Explanations

    concepts related to property and its philosophical implications

    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
    ÄĽr
    -0.07
    esp
    -0.07
    ÑĤаж
    -0.07
     Christie
    -0.07
     direct
    -0.07
    zek
    -0.07
    Tier
    -0.06
     directly
    -0.06
     Tier
    -0.06
     Charter
    -0.06
    POSITIVE LOGITS
     artificial
    0.08
     convenience
    0.08
     convention
    0.08
     arbitrary
    0.08
     merely
    0.07
    Convention
    0.07
     лиÑĪÑĮ
    0.07
     Convenience
    0.07
     Convention
    0.07
    æ·»
    0.07
    Activations Density 0.035%

    No Known Activations