© 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. 15-LLAMASCOPE-RES-131K
    6. 89497
    Prev
    Next
    INDEX
    Explanations

    elements related to Android widget components and properties

    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
    âĨIJ
    -0.07
     kem
    -0.06
     Sugar
    -0.06
     crt
    -0.06
    iola
    -0.06
    atoria
    -0.06
     vit
    -0.06
    Leave
    -0.06
    äh
    -0.06
    éĢļãĤĬ
    -0.06
    POSITIVE LOGITS
    WithValue
    0.07
    084
    0.07
    ìĩ
    0.07
     â̦↵↵
    0.06
    FromBody
    0.06
    žit
    0.06
    *)((
    0.06
     overse
    0.06
    hots
    0.06
    kazy
    0.06
    Activations Density 0.001%

    No Known Activations