© 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. 72830
    Prev
    Next
    INDEX
    Explanations

    references to the Eclipse integrated development environment (IDE)

    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
    loys
    -0.09
    iker
    -0.08
    asher
    -0.08
    erdem
    -0.07
    atown
    -0.07
     AppleWebKit
    -0.07
    readcr
    -0.07
    nbsp
    -0.07
    /REC
    -0.07
    qli
    -0.07
    POSITIVE LOGITS
    å·»
    0.06
     Highlands
    0.06
    _TYP
    0.06
    ottes
    0.06
     womb
    0.06
    мм
    0.06
     Dys
    0.06
     Carroll
    0.06
    Ľi
    0.06
    indi
    0.06
    Activations Density 0.001%

    No Known Activations