© 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. 127505
    Prev
    Next
    INDEX
    Explanations

    phrases related to individual experiences and emotions

    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
    ellas
    -0.08
     suy
    -0.07
    /generated
    -0.07
    енÑĤи
    -0.07
     خر
    -0.07
    .getWindow
    -0.07
    sheets
    -0.07
    ога
    -0.07
    TypeName
    -0.07
    ÑĥÑĢа
    -0.07
    POSITIVE LOGITS
     encounter
    0.08
     clients
    0.07
     encounters
    0.07
     help
    0.07
     offer
    0.07
     helping
    0.07
     cases
    0.07
     encountered
    0.07
     client
    0.06
    ir
    0.06
    Activations Density 0.039%

    No Known Activations