© 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. 93055
    Prev
    Next
    INDEX
    Explanations

    references to fluid dynamics and structures in a physical context

    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
    /design
    -0.07
    ube
    -0.06
     Prev
    -0.06
    zzo
    -0.06
     tripod
    -0.06
    atoire
    -0.06
    rade
    -0.06
    vere
    -0.06
    -designed
    -0.06
    akash
    -0.05
    POSITIVE LOGITS
     formation
    0.13
     formed
    0.12
     Formation
    0.10
    formation
    0.10
     formations
    0.09
    Formation
    0.09
    formed
    0.08
     creation
    0.08
     created
    0.07
    -formed
    0.07
    Activations Density 0.096%

    No Known Activations