© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107177
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and associated metadata

    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
    XMLElement
    -0.07
    xmlns
    -0.06
    beck
    -0.06
    ibir
    -0.06
    ipers
    -0.06
    declare
    -0.06
    xoops
    -0.06
    implify
    -0.06
     cr
    -0.06
    JM
    -0.06
    POSITIVE LOGITS
    turnstile
    0.07
    imon
    0.07
     Nash
    0.07
    PTION
    0.06
    anos
    0.06
    LEC
    0.06
    .tc
    0.06
    Pets
    0.06
     FTP
    0.06
    ãĥ³ãĤ°
    0.06
    Activations Density 0.015%

    No Known Activations