© 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. 58518
    Prev
    Next
    INDEX
    Explanations

    instances of programming syntax and structure

    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
    rema
    -0.08
    rient
    -0.07
    alu
    -0.07
    coni
    -0.07
    ãĤ
    -0.06
     Mate
    -0.06
    oa
    -0.06
    515
    -0.06
     Affero
    -0.06
    kea
    -0.06
    POSITIVE LOGITS
     migrations
    0.06
    uite
    0.06
    upert
    0.06
    unnable
    0.06
     migration
    0.06
     batch
    0.06
     Runnable
    0.06
    æī¹
    0.06
     migrating
    0.06
    izzie
    0.06
    Activations Density 0.002%

    No Known Activations