© 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 EvalsExportsAPI 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. 130475
    Prev
    Next
    INDEX
    Explanations

    references to blog entries or postings in a publication

    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
    olland
    -0.07
    миÑĤ
    -0.06
    ops
    -0.06
    ousel
    -0.06
     Bucc
    -0.06
    474
    -0.06
    lover
    -0.05
    елÑĮзÑı
    -0.05
     ops
    -0.05
     oversh
    -0.05
    POSITIVE LOGITS
    iej
    0.07
    #
    0.07
    arty
    0.07
    ukan
    0.07
     rst
    0.07
    éĺ³åŁİ
    0.06
    gars
    0.06
    .EventQueue
    0.06
     ach
    0.06
    fullscreen
    0.06
    Activations Density 0.001%

    No Known Activations