© 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. 71640
    Prev
    Next
    INDEX
    Explanations

    warning phrases related to caution and awareness of dangers

    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
    ago
    -0.07
    agger
    -0.07
    hum
    -0.06
     ÑĢа
    -0.06
    witter
    -0.06
    ile
    -0.06
     onError
    -0.06
    sie
    -0.06
     fold
    -0.06
    веÑī
    -0.06
    POSITIVE LOGITS
    ance
    0.10
    ycin
    0.07
    stakes
    0.07
     cref
    0.07
    asan
    0.07
     Nicholson
    0.06
    folio
    0.06
    upo
    0.06
    ulen
    0.06
    733
    0.06
    Activations Density 0.004%

    No Known Activations