© 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. 130081
    Prev
    Next
    INDEX
    Explanations

    economic terminology related to pricing and consumption

    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
    ’ÑĶ
    -0.08
    eyse
    -0.08
     dán
    -0.07
    abo
    -0.07
    onica
    -0.07
    orta
    -0.07
    OCR
    -0.06
     Hey
    -0.06
    bk
    -0.06
    ometr
    -0.06
    POSITIVE LOGITS
     váºŃy
    0.10
     similarly
    0.10
     analogy
    0.09
    Similarly
    0.09
     Similarly
    0.08
     likewise
    0.07
     analogue
    0.07
    ä¸Ģæł·
    0.07
     proverb
    0.07
    .ActionListener
    0.07
    Activations Density 0.053%

    No Known Activations