© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 40366
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or confrontation

    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
    onta
    -0.06
     fiscal
    -0.06
     programmes
    -0.06
    UZ
    -0.06
    quip
    -0.06
     Fiscal
    -0.06
     Feld
    -0.06
     permanent
    -0.06
    earned
    -0.06
     habit
    -0.06
    POSITIVE LOGITS
    enthal
    0.08
    ì§ĢëıĦ
    0.07
    ãĤ¢ãĥ¼
    0.07
    ê¸°ë¡ľ
    0.07
    Ú¯ÛĮر
    0.06
    nego
    0.06
    aits
    0.06
    Ú¯ÛĮرÛĮ
    0.06
    ulfill
    0.06
    mods
    0.06
    Activations Density 0.001%

    No Known Activations