© 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 EvalsExportsinterp-engineNEWAPI 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. 55196
    Prev
    Next
    INDEX
    Explanations

    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
    isel
    -0.08
    igroup
    -0.07
    esis
    -0.07
    æ°ı
    -0.07
    mac
    -0.07
    Language
    -0.06
    elay
    -0.06
    uling
    -0.06
    corn
    -0.06
    ä¸Ģ覧
    -0.06
    POSITIVE LOGITS
    _misc
    0.07
    itti
    0.07
     Sle
    0.06
    -lite
    0.06
    FromArray
    0.06
    .src
    0.05
     rollers
    0.05
    宾
    0.05
    _MISC
    0.05
    utters
    0.05
    Activations Density 0.013%

    No Known Activations