© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15640
    Prev
    Next
    INDEX
    Explanations

    phrases related to user engagement or feedback

    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
     Priority
    -0.07
    olate
    -0.06
    zsche
    -0.06
     Parks
    -0.06
    864
    -0.06
    abic
    -0.06
    acio
    -0.06
    uteur
    -0.06
    ãĥĥãĤ¯
    -0.06
     اÙĦعربÙĬØ©
    -0.06
    POSITIVE LOGITS
    ldb
    0.07
    iqu
    0.07
    .Îł
    0.06
    jvu
    0.06
    zenia
    0.06
     crops
    0.06
    egov
    0.06
    afx
    0.06
    vet
    0.06
    edes
    0.06
    Activations Density 0.001%

    No Known Activations