© 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. 95468
    Prev
    Next
    INDEX
    Explanations

    references to water depth and conditions

    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
     Din
    -0.06
    åľĴ
    -0.06
    .ribbon
    -0.06
    åĽŃ
    -0.06
    à¤ľà¤¨
    -0.06
     soaked
    -0.06
     Watt
    -0.05
    koa
    -0.05
    AME
    -0.05
     damp
    -0.05
    POSITIVE LOGITS
    depth
    0.14
     depth
    0.13
     depths
    0.12
    .depth
    0.12
     Depth
    0.11
     deep
    0.11
    deep
    0.11
    .Depth
    0.10
    -depth
    0.10
    Depth
    0.10
    Activations Density 0.011%

    No Known Activations