© 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. 80971
    Prev
    Next
    INDEX
    Explanations

    expressions of duality or the ability to balance multiple concepts or actions

    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
    aeda
    -0.08
    اگ
    -0.07
    еÑģÑĮ
    -0.07
    ÑĪа
    -0.06
    ÏĦιν
    -0.06
     célib
    -0.06
     огÑĢа
    -0.06
     имÑĥ
    -0.06
    Doctrine
    -0.06
     ÑħÑĢа
    -0.06
    POSITIVE LOGITS
     both
    0.47
    both
    0.42
     BOTH
    0.40
     Both
    0.39
    Both
    0.38
    _both
    0.32
     ambos
    0.31
     neither
    0.30
     beide
    0.29
     Neither
    0.26
    Activations Density 0.153%

    No Known Activations