© 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. 4222
    Prev
    Next
    INDEX
    Explanations

    commands or methods related to data handling in a programming context

    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
    lut
    -0.07
    èĶ
    -0.06
    .openg
    -0.06
    ër
    -0.06
    opal
    -0.06
     शत
    -0.06
    å·¥
    -0.06
    aren
    -0.06
     def
    -0.06
    orton
    -0.06
    POSITIVE LOGITS
     forKey
    0.08
    -pdf
    0.07
    eras
    0.07
    gue
    0.07
    ("
    0.06
    598
    0.06
    uncate
    0.06
    ancellable
    0.06
     Bis
    0.06
    kins
    0.06
    Activations Density 0.076%

    No Known Activations