© 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. 27515
    Prev
    Next
    INDEX
    Explanations

    technical terms related to fluid dynamics

    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
    åĦĢ
    -0.07
    碼
    -0.06
    fo
    -0.06
     scrim
    -0.06
     tiny
    -0.06
    upert
    -0.05
    ÑĢаÑĩ
    -0.05
     Virgin
    -0.05
    çĶº
    -0.05
     levels
    -0.05
    POSITIVE LOGITS
     WaitForSeconds
    0.09
     longest
    0.08
     time
    0.08
     Longer
    0.07
     вÑĢемени
    0.07
    utin
    0.07
    enght
    0.07
     longer
    0.07
    à¸Ļาà¸Ļ
    0.07
    Ùħدة
    0.07
    Activations Density 0.067%

    No Known Activations