© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104016
    Prev
    Next
    INDEX
    Explanations

    technical terms related to dipole interactions and their energy behavior in physics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    èĿ
    -0.06
    ĨĴ
    -0.06
    ë¶ģ
    -0.06
     scrim
    -0.06
     Jeh
    -0.06
    ä¸ĬãģĮ
    -0.06
     Sle
    -0.06
     begging
    -0.06
    _FLOW
    -0.06
     Mosul
    -0.06
    POSITIVE LOGITS
     attraction
    0.10
     Distance
    0.10
     distance
    0.09
     mutual
    0.09
    Distance
    0.09
     ÑĢаÑģÑģÑĤоÑı
    0.09
     distances
    0.09
     distancia
    0.08
    distance
    0.08
     pairwise
    0.08
    Activations Density 0.145%

    No Known Activations