© 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 EvalsExportsinterp-engineNEWAPI 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. 4590
    Prev
    Next
    INDEX
    Explanations

    references to institutions, organizations, and professionals in health and education

    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
     ones
    -0.06
     called
    -0.06
    inho
    -0.06
     Comprehensive
    -0.06
    IR
    -0.06
     surrounding
    -0.06
     fur
    -0.05
    ห
    -0.05
     Bros
    -0.05
    resher
    -0.05
    POSITIVE LOGITS
     thuá»Ļc
    0.13
    owned
    0.12
    belongs
    0.12
     owned
    0.11
    å±ŀäºİ
    0.10
     part
    0.10
     sister
    0.10
     belonging
    0.10
     belonged
    0.10
    Owned
    0.09
    Activations Density 0.119%

    No Known Activations