© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 86154
    Prev
    Next
    INDEX
    Explanations

    references to programming and technical terms in Java and Android development

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    baugh
    -0.07
    å¼ķãģį
    -0.06
    aggable
    -0.06
    aland
    -0.06
    Vu
    -0.06
    ied
    -0.06
    ultimate
    -0.06
     that
    -0.06
    äft
    -0.05
    uger
    -0.05
    POSITIVE LOGITS
    -ln
    0.07
    اسر
    0.07
    رÙĤ
    0.07
    ERVED
    0.07
    _REFERER
    0.07
    _mgr
    0.07
    rames
    0.07
    ÑĤаб
    0.07
    '+↵
    0.07
     Tits
    0.07
    Activations Density 0.002%

    No Known Activations