© 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. 98251
    Prev
    Next
    INDEX
    Explanations

    references to specific countries and their leaders

    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
    ippi
    -0.07
     __("
    -0.07
    ãĥ¡ãĥ©
    -0.07
    elia
    -0.07
    alia
    -0.06
    engin
    -0.06
    iesz
    -0.06
    orce
    -0.06
    activex
    -0.06
     brun
    -0.06
    POSITIVE LOGITS
    YG
    0.07
    ajs
    0.07
    ByPrimaryKey
    0.06
    ura
    0.06
    fixed
    0.06
    .FontStyle
    0.06
    kins
    0.06
    ะ
    0.06
     counterpart
    0.06
    yre
    0.05
    Activations Density 0.025%

    No Known Activations