© 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. 9-LLAMASCOPE-RES-131K
    11. 94562
    Prev
    Next
    INDEX
    Explanations

    references to human characteristics and identities

    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
    SPATH
    -0.08
     authDomain
    -0.07
    artner
    -0.07
    âĢĮاÙĨبار
    -0.07
    anan
    -0.07
    аÑĢан
    -0.06
    æ¡IJ
    -0.06
     FactoryBot
    -0.06
     IEntity
    -0.06
     Lange
    -0.06
    POSITIVE LOGITS
     Arch
    0.07
    ocket
    0.07
     version
    0.07
    çīĪ
    0.07
    achten
    0.06
     hos
    0.06
     versions
    0.06
     Amph
    0.06
     Lawrence
    0.06
    ente
    0.06
    Activations Density 0.061%

    No Known Activations