© 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. 9-LLAMASCOPE-RES-131K
    11. 98038
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "retire" and its related concepts

    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
    ÎŃνÏĦ
    -0.07
    enheim
    -0.07
    åĦ¿
    -0.06
    moth
    -0.06
    relude
    -0.06
    wit
    -0.06
    rah
    -0.06
     tiên
    -0.06
    rei
    -0.06
    fried
    -0.06
    POSITIVE LOGITS
    esktop
    0.08
     createState
    0.08
    tainment
    0.07
    velt
    0.07
    bia
    0.07
    ãĥ¡ãĥ³ãĥĪ
    0.07
    款
    0.07
     ÑĤобÑĤо
    0.07
    anca
    0.07
    abel
    0.07
    Activations Density 0.008%

    No Known Activations