© 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. 38833
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those expressing quantities or measurements

    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
    ëĵ¤ê³¼
    -0.07
    iferay
    -0.07
    REET
    -0.07
    ìĿ´ëĤĺ
    -0.06
    ARSER
    -0.06
    ®,
    -0.06
    à¥ĩण
    -0.06
    \Doctrine
    -0.06
    ãģŁãģı
    -0.06
    ITTE
    -0.06
    POSITIVE LOGITS
     alike
    0.16
     respectively
    0.10
     depending
    0.08
     olmak
    0.08
    _IRQHandler
    0.07
     ÑģооÑĤвеÑĤ
    0.07
    depending
    0.07
     Streets
    0.07
    licant
    0.07
    ademic
    0.06
    Activations Density 0.045%

    No Known Activations