© 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. 104491
    Prev
    Next
    INDEX
    Explanations

    references to products and shopping 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
    кÑģ
    -0.07
     leg
    -0.06
     role
    -0.06
     pan
    -0.06
    brands
    -0.06
    ï¼Ł↵↵
    -0.06
    ushima
    -0.05
     rising
    -0.05
     budget
    -0.05
     pro
    -0.05
    POSITIVE LOGITS
     prototypes
    0.07
    atoire
    0.07
    LING
    0.07
    olio
    0.07
    款
    0.07
    .googlecode
    0.07
    ombo
    0.07
     Etsy
    0.07
    thers
    0.07
    .sell
    0.07
    Activations Density 0.017%

    No Known Activations