© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30711
    Prev
    Next
    INDEX
    Explanations

    content related to economic issues and proposed fee increases in education

    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
    romium
    -0.06
    kir
    -0.06
    achs
    -0.06
     thrown
    -0.06
    æijĩ
    -0.05
     Immigration
    -0.05
     gib
    -0.05
    yg
    -0.05
     styled
    -0.05
    ey
    -0.05
    POSITIVE LOGITS
    涨
    0.10
     pricing
    0.10
     prices
    0.10
    Prices
    0.09
     price
    0.09
    prices
    0.08
     Prices
    0.08
     hikes
    0.08
     Pricing
    0.08
     increases
    0.07
    Activations Density 0.016%

    No Known Activations