© 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. 107215
    Prev
    Next
    INDEX
    Explanations

    terms related to programming constructs and configurations

    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
     shared
    -0.06
    ake
    -0.06
    knife
    -0.06
     recall
    -0.06
     pros
    -0.06
    pr
    -0.06
    ervisor
    -0.05
    ild
    -0.05
     sne
    -0.05
     aks
    -0.05
    POSITIVE LOGITS
     NotImplemented
    0.07
    .promise
    0.07
    à¸ŀร
    0.07
    swire
    0.07
    .progress
    0.07
    atches
    0.07
    ãĥ¬ãĥĥãĥĪ
    0.07
    sonian
    0.07
    enzie
    0.07
    OKIE
    0.07
    Activations Density 0.035%

    No Known Activations