© 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. 124770
    Prev
    Next
    INDEX
    Explanations

    references to wealth and luxury items

    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
    etter
    -0.06
    athom
    -0.06
    angan
    -0.06
    cast
    -0.06
     Edison
    -0.06
     Isles
    -0.06
     Belt
    -0.06
     independents
    -0.06
    agg
    -0.05
     bumped
    -0.05
    POSITIVE LOGITS
     purchase
    0.08
     gift
    0.08
    CTS
    0.07
    ekler
    0.07
     purchases
    0.07
    Cooldown
    0.07
     gifted
    0.07
     purchased
    0.07
     sợ
    0.07
    ModifiedDate
    0.07
    Activations Density 0.001%

    No Known Activations