© 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. 15-LLAMASCOPE-RES-131K
    11. 86575
    Prev
    Next
    INDEX
    Explanations

    relationships between individuals and their connections to awards or recognition

    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
    â
    -0.07
    ama
    -0.06
    aux
    -0.05
     forms
    -0.05
    ÂŃ
    -0.05
    loor
    -0.05
    atti
    -0.05
     y
    -0.05
    eder
    -0.05
    loo
    -0.05
    POSITIVE LOGITS
    _Tis
    0.09
    apgolly
    0.09
    InParameter
    0.09
    fragistics
    0.09
    aÅĻ
    0.08
    íĨłíĨł
    0.08
    SSERT
    0.08
    WidthSpace
    0.08
    'gc
    0.08
    urovision
    0.08
    Activations Density 0.006%

    No Known Activations