© 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. 127935
    Prev
    Next
    INDEX
    Explanations

    sentences discussing coding practices and issues in software development

    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
    annt
    -0.07
     unavoid
    -0.07
    unar
    -0.06
    ord
    -0.06
    .cast
    -0.06
    asher
    -0.06
    onen
    -0.06
    euillez
    -0.06
    ledger
    -0.06
    è½®
    -0.06
    POSITIVE LOGITS
     often
    0.10
    often
    0.08
     unfortunately
    0.08
     many
    0.08
     Often
    0.07
     íĿĶ
    0.07
     sadly
    0.07
    Often
    0.07
    egas
    0.06
     frequently
    0.06
    Activations Density 0.043%

    No Known Activations