© 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. 123816
    Prev
    Next
    INDEX
    Explanations

    references to historical events or figures related to governance and influential institutions

    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
    aland
    -0.06
     Brit
    -0.06
    دا
    -0.06
    emachine
    -0.06
    inar
    -0.06
    lass
    -0.06
    arel
    -0.06
    enha
    -0.06
    ener
    -0.06
    779
    -0.05
    POSITIVE LOGITS
     Swal
    0.07
    館
    0.07
    DMI
    0.07
    managed
    0.06
    μμ
    0.06
     OSI
    0.06
    oose
    0.06
    nos
    0.06
    .TO
    0.06
    ème
    0.06
    Activations Density 0.068%

    No Known Activations