© 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 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. 16499
    Prev
    Next
    INDEX
    Explanations

    references to monetary values and financial data

    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
     macOS
    -0.14
    202
    -0.13
     https
    -0.13
    https
    -0.13
     Patreon
    -0.12
     GDPR
    -0.12
    ðŁĺ
    -0.11
     ðŁij
    -0.10
     IoT
    -0.10
     emojis
    -0.10
    POSITIVE LOGITS
    .googlecode
    0.12
    Obama
    0.12
     Obama
    0.12
     Wii
    0.11
     Palin
    0.10
     iPod
    0.10
     Barack
    0.10
     xrange
    0.10
    200
    0.10
     Occupy
    0.10
    Activations Density 2.226%

    No Known Activations