© 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. 9-LLAMASCOPE-RES-131K
    11. 98579
    Prev
    Next
    INDEX
    Explanations

    details related to product specifications and features

    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
    velt
    -0.08
    .scalablytyped
    -0.08
     addCriterion
    -0.07
    rawer
    -0.07
    dete
    -0.07
    .MixedReality
    -0.07
    dens
    -0.07
    'gc
    -0.07
    vyk
    -0.07
     åĨĨ
    -0.07
    POSITIVE LOGITS
    ummy
    0.06
     Dut
    0.05
     pace
    0.05
     Pace
    0.05
    ting
    0.05
    438
    0.05
    termin
    0.05
    izzy
    0.05
    rowave
    0.05
     Lakes
    0.05
    Activations Density 0.002%

    No Known Activations