© 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. 31118
    Prev
    Next
    INDEX
    Explanations

    concepts related to buoyancy and 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
    vod
    -0.07
    رÛĮÙħ
    -0.07
    ostel
    -0.07
    纪
    -0.07
    efon
    -0.06
    ÙĬÙĨات
    -0.06
    æIJŃ
    -0.06
    ç´Ģ
    -0.06
    acific
    -0.06
    ìĹ¼
    -0.06
    POSITIVE LOGITS
     mechanisms
    0.12
     mechanism
    0.10
     effects
    0.10
    ä½ľçĶ¨
    0.09
     interactions
    0.09
     contributions
    0.09
     contribution
    0.09
     factors
    0.09
     effect
    0.08
     Mechan
    0.08
    Activations Density 0.123%

    No Known Activations