© 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. 28554
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to fatal incidents or deaths

    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
    ularity
    -0.07
    edom
    -0.07
    aeda
    -0.07
    ovnÃŃ
    -0.07
    itzer
    -0.07
    athers
    -0.07
     baÅŁÄ±na
    -0.07
    alet
    -0.07
     preval
    -0.06
    몰
    -0.06
    POSITIVE LOGITS
     flaw
    0.08
    ism
    0.07
    ities
    0.07
    áng
    0.07
    omas
    0.07
     blow
    0.07
    ogy
    0.07
    /non
    0.07
    .gdx
    0.07
    æĶ
    0.07
    Activations Density 0.006%

    No Known Activations