© 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. 74054
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to official content and formal documentation

    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
    uzzi
    -0.07
    iac
    -0.07
     ìĥĪê¸Ģ
    -0.07
    semb
    -0.07
    iç
    -0.07
    Ñıж
    -0.06
    .sharedInstance
    -0.06
    Ñĥже
    -0.06
    ilk
    -0.06
    vetica
    -0.06
    POSITIVE LOGITS
     official
    0.11
     website
    0.10
     site
    0.08
     ê³µìĭĿ
    0.07
    website
    0.07
     stránky
    0.07
     oficial
    0.07
     Official
    0.07
     اÙĦÙħÙĪÙĤع
    0.07
    å®ĺæĸ¹
    0.07
    Activations Density 0.002%

    No Known Activations