© 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. 104814
    Prev
    Next
    INDEX
    Explanations

    unique identifiers or references in a document

    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
    tls
    -0.07
    пÑĢиклад
    -0.07
    isor
    -0.07
    bsp
    -0.07
    /generated
    -0.07
    ãĤīãģı
    -0.07
    iná
    -0.07
    borg
    -0.07
    âĦĸâĦĸ
    -0.07
     ãģĹ
    -0.07
    POSITIVE LOGITS
    624
    0.06
     Tab
    0.06
    755
    0.06
    754
    0.06
    ÄĻ
    0.06
    313
    0.06
    icamente
    0.06
    ¬
    0.06
    Tab
    0.05
     Joan
    0.05
    Activations Density 0.004%

    No Known Activations