© 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. 9-LLAMASCOPE-RES-131K
    11. 98660
    Prev
    Next
    INDEX
    Explanations

    mentions of online shopping and retail-related terms

    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
     Hlav
    -0.07
    วล
    -0.06
    ulet
    -0.06
     Dem
    -0.06
    USH
    -0.06
    irsch
    -0.06
    umble
    -0.06
    ategorized
    -0.06
    è¡
    -0.06
    ouden
    -0.06
    POSITIVE LOGITS
    xfff
    0.07
    oup
    0.07
    REEN
    0.06
    olian
    0.06
    mods
    0.06
     flexGrow
    0.06
     жид
    0.06
    .idea
    0.06
     STATIC
    0.06
    ãĤĤãģ®
    0.06
    Activations Density 0.017%

    No Known Activations