© 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. 82969
    Prev
    Next
    INDEX
    Explanations

    Java programming language components 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
    owie
    -0.09
    etz
    -0.08
    myModal
    -0.07
    ebek
    -0.07
    ncy
    -0.07
    eda
    -0.07
    ibold
    -0.07
     ÑĢÑĥками
    -0.07
    onta
    -0.07
    ÙĪÙħÛĮ
    -0.07
    POSITIVE LOGITS
    .reflect
    0.07
     Tah
    0.07
    reflect
    0.06
    .daily
    0.06
     PAC
    0.06
    razier
    0.06
     releasing
    0.05
    iglia
    0.05
     SHIPPING
    0.05
     Grim
    0.05
    Activations Density 0.000%

    No Known Activations