© 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 EvalsExportsAPI 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. 85490
    Prev
    Next
    INDEX
    Explanations

    variations of the word "work."

    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
    etes
    -0.07
    etu
    -0.07
    éĢĶ
    -0.07
    ạ
    -0.07
    견
    -0.07
    elan
    -0.07
    ยà¸ĩ
    -0.07
    stype
    -0.07
    ffd
    -0.07
     galer
    -0.06
    POSITIVE LOGITS
    -zone
    0.06
    ippi
    0.06
     altogether
    0.06
    379
    0.06
     zone
    0.06
    ORE
    0.06
     Griffith
    0.06
    ague
    0.06
    acted
    0.05
     ag
    0.05
    Activations Density 0.016%

    No Known Activations