© 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. 61477
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and keywords

    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
    mand
    -0.09
    zej
    -0.07
    .scalablytyped
    -0.07
    hei
    -0.07
    æݪ
    -0.07
    raç
    -0.07
    haps
    -0.06
    hi
    -0.06
    [Test
    -0.06
    .uk
    -0.06
    POSITIVE LOGITS
     veto
    0.06
     Uns
    0.06
    ystore
    0.05
    odable
    0.05
     uns
    0.05
    ckett
    0.05
    iglia
    0.05
     stake
    0.05
    aginator
    0.05
    ļĮ
    0.05
    Activations Density 0.270%

    No Known Activations