© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106848
    Prev
    Next
    INDEX
    Explanations

    references to shopping malls and related activities

    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
     Celt
    -0.07
     compound
    -0.06
    warts
    -0.06
    ãĥĽãĥĨãĥ«
    -0.06
    /mat
    -0.06
    achine
    -0.06
     resett
    -0.06
    æĪIJç«ĭ
    -0.06
     Compound
    -0.06
    .eng
    -0.06
    POSITIVE LOGITS
     mall
    0.17
     shopping
    0.14
     Shopping
    0.14
     malls
    0.13
     Mall
    0.13
    -shopping
    0.12
    Shopping
    0.12
     shopper
    0.12
     shoppers
    0.12
    mall
    0.11
    Activations Density 0.069%

    No Known Activations