© 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. 15-LLAMASCOPE-RES-131K
    11. 90765
    Prev
    Next
    INDEX
    Explanations

    references to editing or debugging processes in programming contexts

    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
    iele
    -0.06
    .backend
    -0.06
     discre
    -0.06
    ãĥĶãĥ¼
    -0.06
    esson
    -0.06
     Tome
    -0.05
    ubbo
    -0.05
    Hello
    -0.05
    a
    -0.05
    ľ
    -0.05
    POSITIVE LOGITS
    uitka
    0.09
    <quote
    0.08
    éłĺ
    0.07
    ller
    0.07
    .borrow
    0.07
    istrovstvÃŃ
    0.07
    ILI
    0.07
    tiv
    0.06
    permalink
    0.06
    eryl
    0.06
    Activations Density 0.006%

    No Known Activations