© 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. 74650
    Prev
    Next
    INDEX
    Explanations

    themes of hatred and animosity towards individuals or groups

    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
    bourg
    -0.07
    ocab
    -0.07
    idunt
    -0.07
    δά
    -0.07
    Äįet
    -0.07
    .sg
    -0.07
     omas
    -0.07
    eroon
    -0.07
    assin
    -0.07
    .ws
    -0.07
    POSITIVE LOGITS
     anim
    0.07
    æģ¨
    0.07
     dating
    0.07
     rival
    0.06
     hatred
    0.06
     Anim
    0.06
     hostile
    0.06
     distrust
    0.06
     venom
    0.06
     unle
    0.06
    Activations Density 0.061%

    No Known Activations