© 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. 54424
    Prev
    Next
    INDEX
    Explanations

    historical references and notable figures related to colonial and early American history

    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
     costa
    -0.06
    templ
    -0.06
     Rural
    -0.06
     Seah
    -0.06
     rural
    -0.06
    à¥Ģà¤Ł
    -0.06
     Costa
    -0.06
     Golf
    -0.06
    istra
    -0.06
    .mu
    -0.05
    POSITIVE LOGITS
     Indian
    0.11
     Indians
    0.09
    Indian
    0.09
     indian
    0.09
     Native
    0.08
     buffalo
    0.08
     fur
    0.08
     Apache
    0.07
     Aboriginal
    0.07
     Euro
    0.07
    Activations Density 0.038%

    No Known Activations