© 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. 92060
    Prev
    Next
    INDEX
    Explanations

    elements related to societal issues and community commentary

    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
     unlike
    -0.07
    ÐķС
    -0.07
     little
    -0.07
     exception
    -0.06
    	Copyright
    -0.06
    âĻª
    -0.06
    hma
    -0.06
    éric
    -0.06
    _exception
    -0.06
     Unlike
    -0.06
    POSITIVE LOGITS
     ones
    0.09
     equally
    0.09
    ones
    0.09
     Ones
    0.09
     including
    0.08
    including
    0.07
     other
    0.07
    eg
    0.07
     دÛĮگرÛĮ
    0.07
     altogether
    0.07
    Activations Density 0.050%

    No Known Activations