© 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 EvalsExportsAPI 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. 29378
    Prev
    Next
    INDEX
    Explanations

    references to lounges or comfortable seating areas

    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
    cheng
    -0.08
    dispatcher
    -0.07
    son
    -0.07
     sayıda
    -0.07
    thur
    -0.07
    ein
    -0.07
    оÑĹ
    -0.07
    cher
    -0.07
     GOODMAN
    -0.07
    nis
    -0.07
    POSITIVE LOGITS
    ing
    0.08
    ette
    0.08
    y
    0.08
    able
    0.07
    alaxy
    0.07
    maid
    0.07
     area
    0.07
    ify
    0.07
    ettes
    0.07
    kil
    0.06
    Activations Density 0.003%

    No Known Activations