© 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. 76471
    Prev
    Next
    INDEX
    Explanations

    instances of high-stakes financial or contractual scenarios

    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
    arden
    -0.07
    hog
    -0.07
    allery
    -0.07
    olland
    -0.07
    tape
    -0.07
    avia
    -0.07
    illes
    -0.07
    rud
    -0.07
    lesi
    -0.07
    anske
    -0.07
    POSITIVE LOGITS
    .ly
    0.06
     rounded
    0.06
     aside
    0.06
     ê±´
    0.06
    _PTR
    0.06
    scratch
    0.06
    abling
    0.06
    ICC
    0.06
    ly
    0.05
     Eis
    0.05
    Activations Density 0.002%

    No Known Activations