© 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. 41670
    Prev
    Next
    INDEX
    Explanations

    instances of formal educational terminology and leadership concepts

    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
    ohl
    -0.07
    çľĮ
    -0.06
    	RTCT
    -0.06
    egas
    -0.06
    acher
    -0.06
    odes
    -0.06
    ¡
    -0.06
     Keller
    -0.06
    iento
    -0.06
    ìłĢ
    -0.06
    POSITIVE LOGITS
     rowspan
    0.07
    ĨĴ
    0.07
    amet
    0.07
    lotte
    0.06
    Ĩ
    0.06
     Jay
    0.06
     ulus
    0.06
    á»·
    0.06
    ãĥ¼ãĤº
    0.06
    /autoload
    0.06
    Activations Density 0.214%

    No Known Activations