© 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. 120024
    Prev
    Next
    INDEX
    Explanations

    snippets of code and programming-related elements

    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
     heads
    -0.06
    meden
    -0.06
    ữu
    -0.06
    enticated
    -0.06
     STL
    -0.06
    olik
    -0.06
    ese
    -0.06
    umph
    -0.06
    erp
    -0.06
     NU
    -0.06
    POSITIVE LOGITS
    periment
    0.07
    run
    0.07
    LineColor
    0.07
    .RunWith
    0.07
    åĬĥ
    0.07
    /run
    0.06
    .run
    0.06
    	run
    0.06
     run
    0.06
    ahn
    0.06
    Activations Density 0.027%

    No Known Activations