© 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. 39468
    Prev
    Next
    INDEX
    Explanations

    words related to variety and diversity in options

    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
    gin
    -0.07
    orum
    -0.07
    .tc
    -0.07
    hack
    -0.06
    ãģĤãģĤ
    -0.06
    mae
    -0.06
    etsk
    -0.06
    大éĩı
    -0.06
    /run
    -0.06
     Contribution
    -0.06
    POSITIVE LOGITS
     sizes
    0.08
     flavors
    0.07
     colors
    0.07
     tongues
    0.07
     colours
    0.07
    itÃł
    0.07
     shape
    0.07
     size
    0.07
     flavours
    0.07
     shapes
    0.07
    Activations Density 0.008%

    No Known Activations