© 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. 41130
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly postal codes and phone numbers

    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
    czy
    -0.06
     drying
    -0.06
     col
    -0.06
    etsk
    -0.06
     head
    -0.05
     pencil
    -0.05
     helper
    -0.05
    ertain
    -0.05
    onica
    -0.05
    iasi
    -0.05
    POSITIVE LOGITS
    PostBack
    0.08
    Envelope
    0.07
    olle
    0.07
    oller
    0.07
    à¸ļาย
    0.07
    isÃŃ
    0.07
     LETTER
    0.07
    _regularizer
    0.07
    mock
    0.07
     Letter
    0.07
    Activations Density 0.003%

    No Known Activations