© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71751
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting code optimization and refactoring

    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
     Colon
    -0.07
    angl
    -0.07
    SupportActionBar
    -0.07
    illo
    -0.06
    ']=="
    -0.06
    -gnu
    -0.06
     physically
    -0.06
    itone
    -0.06
     consort
    -0.06
    stin
    -0.06
    POSITIVE LOGITS
     code
    0.08
    代çłģ
    0.07
     elegance
    0.07
     Efficiency
    0.07
     ugl
    0.07
    ofire
    0.07
     efficiencies
    0.07
    oogle
    0.07
     efficiency
    0.07
    èĭ
    0.07
    Activations Density 0.020%

    No Known Activations