© 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. 57288
    Prev
    Next
    INDEX
    Explanations

    phrases involving partnerships or collaborations aimed at achieving specific goals

    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
    heed
    -0.07
     alone
    -0.07
    ppe
    -0.07
    .VERSION
    -0.07
     Dön
    -0.07
    ardu
    -0.07
    /mit
    -0.07
    rompt
    -0.06
    çĤİ
    -0.06
    rogate
    -0.06
    POSITIVE LOGITS
     create
    0.07
     Craft
    0.06
    onna
    0.06
     mutual
    0.06
    475
    0.06
     mutually
    0.06
     Mutual
    0.06
    iu
    0.06
     try
    0.06
    ief
    0.06
    Activations Density 0.017%

    No Known Activations