© 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. 3999
    Prev
    Next
    INDEX
    Explanations

    references to harm, injuries, or casualties in various contexts

    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
    erville
    -0.07
    ikes
    -0.07
    æª
    -0.06
    θÎŃ
    -0.06
    ville
    -0.06
    ough
    -0.05
     Pioneer
    -0.05
    innie
    -0.05
    ils
    -0.05
     Bolton
    -0.05
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸ģาร
    0.09
    .scalablytyped
    0.08
     accordingly
    0.07
    izzy
    0.07
    žen
    0.07
    lightbox
    0.07
     dabei
    0.07
     dafür
    0.07
    edar
    0.06
    á»iji
    0.06
    Activations Density 0.045%

    No Known Activations