© 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. 124020
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and service in various contexts

    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
     similarly
    -0.07
    yll
    -0.06
    683
    -0.06
    optgroup
    -0.06
     Commons
    -0.06
    oran
    -0.06
     concerns
    -0.06
     goodness
    -0.05
    tem
    -0.05
     impair
    -0.05
    POSITIVE LOGITS
    isman
    0.08
    itsu
    0.08
    ETO
    0.07
     Annunci
    0.07
    æºĸ
    0.07
    rames
    0.07
    bucks
    0.07
    æľµ
    0.07
    .decor
    0.07
    unce
    0.07
    Activations Density 0.004%

    No Known Activations