© 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. 85250
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and numerical results in scientific contexts

    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
    azzi
    -0.08
     concession
    -0.06
     Kushner
    -0.06
    æĮĤ
    -0.06
    eczy
    -0.06
    çݯ
    -0.06
    eyh
    -0.06
    privileged
    -0.06
    æĭ³
    -0.06
    ologna
    -0.05
    POSITIVE LOGITS
     Reynolds
    0.08
    flow
    0.07
     flow
    0.07
     Flow
    0.07
    DNS
    0.07
     Fluent
    0.07
    Boundary
    0.07
    wake
    0.07
     Reyn
    0.07
    NSE
    0.07
    Activations Density 0.186%

    No Known Activations