© 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. 15-LLAMASCOPE-RES-131K
    11. 88251
    Prev
    Next
    INDEX
    Explanations

    punctuation and syntax elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code syntax pattern showing the end of variable/field/parameter declarations or statement endings, typically marked by closing punctuation or syntax elements.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    /projects
    -0.06
     Judge
    -0.06
    691
    -0.06
    vit
    -0.06
    /software
    -0.05
     judge
    -0.05
    ancellor
    -0.05
    ades
    -0.05
     Elder
    -0.05
    .scalablytyped
    -0.05
    POSITIVE LOGITS
    antu
    0.08
    owitz
    0.07
    OrderBy
    0.07
    raç
    0.07
    ваннÑı
    0.07
    ÏĥÏĦαν
    0.07
    reinterpret
    0.07
    gre
    0.07
    ãĥ¼ãĥª
    0.06
    벨
    0.06
    Activations Density 0.043%

    No Known Activations