© 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. 39085
    Prev
    Next
    INDEX
    Explanations

    references to organizations and companies in Ukraine, particularly their history and economic activities

    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
    ùy
    -0.07
    /***/
    -0.06
    oure
    -0.06
    lamaz
    -0.06
     Loren
    -0.06
     dispers
    -0.06
     Bor
    -0.06
    볨
    -0.06
    Convention
    -0.06
     Sawyer
    -0.06
    POSITIVE LOGITS
     companies
    0.07
    uve
    0.07
     compan
    0.07
     company
    0.07
    cé
    0.07
    rale
    0.07
    company
    0.07
     operating
    0.06
    glomer
    0.06
    ioctl
    0.06
    Activations Density 0.008%

    No Known Activations