© 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 EvalsExportsAPI 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. 119214
    Prev
    Next
    INDEX
    Explanations

    references to international trade agreements

    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
    875
    -0.06
    agas
    -0.06
    aida
    -0.06
    acie
    -0.06
    ande
    -0.06
    arah
    -0.06
    ENE
    -0.06
    ÑĢÑı
    -0.06
     needing
    -0.06
    575
    -0.06
    POSITIVE LOGITS
    oton
    0.07
    å§ij
    0.07
     mdi
    0.07
     @_
    0.07
    eshire
    0.06
    ůl
    0.06
    (JS
    0.06
    .createObject
    0.06
    ync
    0.06
     lawy
    0.06
    Activations Density 0.000%

    No Known Activations