© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83358
    Prev
    Next
    INDEX
    Explanations

    terms related to medical emergencies and death

    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
    _firestore
    -0.07
     нада
    -0.07
    esModule
    -0.07
    ertino
    -0.07
    arsi
    -0.07
    алÑİ
    -0.07
    .ibatis
    -0.07
    uler
    -0.07
    duk
    -0.07
    або
    -0.07
    POSITIVE LOGITS
     collapse
    0.07
     im
    0.07
     fatal
    0.07
     heart
    0.07
     ful
    0.07
     die
    0.07
    -collapse
    0.06
     ultimately
    0.06
     massive
    0.06
     suff
    0.06
    Activations Density 0.012%

    No Known Activations