© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3634
    Prev
    Next
    INDEX
    Explanations

    components and features of appliances and machinery

    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
     hydr
    -0.08
     Hydraulic
    -0.07
    iture
    -0.06
     Thames
    -0.06
     hydraulic
    -0.06
    bulk
    -0.06
     squirt
    -0.06
     swelling
    -0.06
     Ramp
    -0.06
    धर
    -0.06
    POSITIVE LOGITS
     dust
    0.12
     hood
    0.11
     exhaust
    0.11
     fan
    0.11
     Hood
    0.11
    dust
    0.11
     Dust
    0.11
     partic
    0.11
    hood
    0.11
     vent
    0.10
    Activations Density 0.019%

    No Known Activations