© 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. 15-LLAMASCOPE-RES-131K
    11. 86359
    Prev
    Next
    INDEX
    Explanations

    merchandise-related content and promotions

    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
     cast
    -0.06
     crack
    -0.06
    venes
    -0.05
     macro
    -0.05
    ↵
    -0.05
     Crack
    -0.05
     steps
    -0.05
     ph
    -0.05
    ils
    -0.05
     CAST
    -0.05
    POSITIVE LOGITS
     purch
    0.08
     items
    0.08
     itk
    0.08
    åĩĿ
    0.08
    ureau
    0.07
     omas
    0.07
     ÙģرÙĪ
    0.07
    Ordered
    0.07
     oficial
    0.07
     اÙĦرسÙħÙĬ
    0.07
    Activations Density 0.027%

    No Known Activations