© 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. 105318
    Prev
    Next
    INDEX
    Explanations

    references to the labor conditions of lace makers

    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
    inaire
    -0.07
    stå
    -0.06
     Embed
    -0.06
    amba
    -0.06
    iglia
    -0.06
     equip
    -0.06
    uzu
    -0.06
    eyen
    -0.06
    Ľå»º
    -0.06
    nze
    -0.06
    POSITIVE LOGITS
     Factory
    0.10
     factory
    0.10
    factory
    0.09
    Factory
    0.08
     worker
    0.08
     Industrial
    0.08
     labor
    0.08
     workers
    0.08
     unions
    0.07
     work
    0.07
    Activations Density 0.025%

    No Known Activations