© 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. 57950
    Prev
    Next
    INDEX
    Explanations

    references to system processes and signals

    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
    icher
    -0.07
    ahoma
    -0.07
    yaw
    -0.07
     PROGMEM
    -0.07
    isay
    -0.07
    asio
    -0.07
     ÏĥÏħνο
    -0.07
    nga
    -0.07
    <fieldset
    -0.07
     Dag
    -0.07
    POSITIVE LOGITS
    egree
    0.06
     fork
    0.06
    kit
    0.06
    orne
    0.06
     successful
    0.05
     dut
    0.05
    ught
    0.05
     Gonzalez
    0.05
    isors
    0.05
     trap
    0.05
    Activations Density 0.000%

    No Known Activations