© 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. 89169
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to agricultural production

    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
     Boise
    -0.07
     Duy
    -0.06
     Spokane
    -0.06
     Pike
    -0.06
    -compose
    -0.06
     didFinish
    -0.06
     automát
    -0.06
    CONDS
    -0.06
     Sno
    -0.06
    athi
    -0.06
    POSITIVE LOGITS
     Cuba
    0.15
     Cuban
    0.15
     Havana
    0.14
     Miami
    0.13
    Miami
    0.12
     Cub
    0.11
     Florida
    0.09
     ÐļÑĥб
    0.09
    Florida
    0.09
    idel
    0.09
    Activations Density 0.298%

    No Known Activations