© 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. 5-LLAMASCOPE-RES-131K
    11. 125853
    Prev
    Next
    INDEX
    Explanations

    instances of death or dying

    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
    andr
    -0.06
    AndWait
    -0.05
     apparently
    -0.05
    getJSON
    -0.05
    226
    -0.05
    elves
    -0.05
     Fry
    -0.05
    ãĥ¼ãĥķ
    -0.05
    anmar
    -0.05
     Ñģмог
    -0.05
    POSITIVE LOGITS
    /Dk
    0.09
    ityEngine
    0.08
    ÑĨеÑĢ
    0.08
    laz
    0.07
    оба
    0.07
    AttributeValue
    0.07
    баÑģ
    0.07
    목
    0.07
    |)↵
    0.07
    ycler
    0.07
    Activations Density 0.004%

    No Known Activations