© 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. 78866
    Prev
    Next
    INDEX
    Explanations

    lines of code related to import statements in a programming document

    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
    fur
    -0.07
     Fur
    -0.06
    -uri
    -0.06
    etz
    -0.06
    ableObject
    -0.06
    illard
    -0.06
    .bundle
    -0.06
     Face
    -0.06
    eneg
    -0.06
    innen
    -0.06
    POSITIVE LOGITS
    ersh
    0.09
    avid
    0.07
    .jetbrains
    0.07
    Acceleration
    0.07
    Sharper
    0.07
    ovsky
    0.07
    .intellij
    0.06
    ought
    0.06
    riba
    0.06
    upro
    0.06
    Activations Density 0.008%

    No Known Activations