© 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. 28138
    Prev
    Next
    INDEX
    Explanations

    information related to agricultural production and trade statistics

    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
    -A
    -0.06
    glob
    -0.05
    872
    -0.05
    SSI
    -0.05
    465
    -0.05
    path
    -0.05
     Hast
    -0.05
    aram
    -0.05
    apest
    -0.05
    oble
    -0.05
    POSITIVE LOGITS
     Gross
    0.08
    BED
    0.07
    ByKey
    0.07
    ÙĪÙħات
    0.07
    /providers
    0.07
     Outer
    0.07
    NECT
    0.07
     disag
    0.07
    åĩĢ
    0.07
     gross
    0.07
    Activations Density 0.005%

    No Known Activations