© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    references to warnings, deadlines, and consequences in a legal or regulatory context

    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
    yna
    -0.07
    agna
    -0.07
    /forum
    -0.07
    erk
    -0.06
    _usb
    -0.06
    adb
    -0.06
    msp
    -0.06
    ½Ķ
    -0.06
    سط
    -0.06
    allax
    -0.06
    POSITIVE LOGITS
     warnings
    0.18
     warning
    0.17
     warned
    0.16
     Warning
    0.15
     Warn
    0.15
     warn
    0.14
    warnings
    0.14
    warn
    0.14
    Warning
    0.14
    Warn
    0.13
    Activations Density 0.075%

    No Known Activations