© 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. 118675
    Prev
    Next
    INDEX
    Explanations

    opening and closing brackets or braces in structures like code or syntax

    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
    ãĤ¹ãĤ¿ãĥ¼
    -0.08
    aldi
    -0.08
    Forgery
    -0.07
     klu
    -0.07
    .STATE
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    Ưá»
    -0.07
    زب
    -0.07
    :System
    -0.07
    ий
    -0.07
    POSITIVE LOGITS
    unga
    0.06
    ed
    0.06
    edik
    0.06
    721
    0.06
     prelim
    0.06
    ket
    0.05
     Anc
    0.05
    avor
    0.05
     Pom
    0.05
    comb
    0.05
    Activations Density 0.035%

    No Known Activations