© 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. 121276
    Prev
    Next
    INDEX
    Explanations

    HTML elements and classes related to cart functionality in web applications

    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
    visa
    -0.07
     Polar
    -0.07
    intr
    -0.06
     NotSupportedException
    -0.06
    zo
    -0.06
    vation
    -0.06
    rac
    -0.06
    andex
    -0.06
    rica
    -0.06
    .Apis
    -0.06
    POSITIVE LOGITS
    undle
    0.07
    ì±Ħ
    0.06
     stroke
    0.06
     mrb
    0.06
    alt
    0.06
    ÑĢд
    0.06
    ERY
    0.06
    intColor
    0.06
    ARGE
    0.06
    earer
    0.06
    Activations Density 0.009%

    No Known Activations