© 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. 18077
    Prev
    Next
    INDEX
    Explanations

    actions related to online ordering and membership sign-ups

    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
    utz
    -0.06
     report
    -0.06
     Carrier
    -0.06
     Pom
    -0.05
    alam
    -0.05
     Sheriff
    -0.05
     Explore
    -0.05
     personal
    -0.05
     free
    -0.05
     recently
    -0.05
    POSITIVE LOGITS
    enan
    0.08
    .getComponent
    0.07
    Stripe
    0.07
    μη
    0.07
    WAYS
    0.07
    å±¥
    0.07
    ãģ®ãĤĤ
    0.07
    olian
    0.07
    Forgery
    0.07
    åĿĽ
    0.07
    Activations Density 0.014%

    No Known Activations