© 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. 28046
    Prev
    Next
    INDEX
    Explanations

    references to online shopping and e-commerce

    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
    Ñĥнк
    -0.07
    оÑģÑĢед
    -0.07
     sey
    -0.07
    ëĨĵ
    -0.07
    jeme
    -0.07
    ilities
    -0.07
    rones
    -0.07
    ussen
    -0.07
    zioni
    -0.07
    ÑģоÑĤ
    -0.07
    POSITIVE LOGITS
    680
    0.07
    .net
    0.06
    emark
    0.06
    www
    0.06
     Laur
    0.06
     Cra
    0.06
     www
    0.06
     web
    0.05
    web
    0.05
    380
    0.05
    Activations Density 0.017%

    No Known Activations