© 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. 15-LLAMASCOPE-RES-131K
    11. 88121
    Prev
    Next
    INDEX
    Explanations

    references to Detroit as a city

    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
    овиÑĩ
    -0.07
    iyah
    -0.07
     Chick
    -0.07
    "c
    -0.06
     oprav
    -0.06
    cript
    -0.06
     dru
    -0.06
    bases
    -0.06
     bases
    -0.06
     жиз
    -0.06
    POSITIVE LOGITS
    eview
    0.07
    ahoma
    0.07
    zia
    0.07
    urgeon
    0.07
    jak
    0.06
    SystemService
    0.06
    icot
    0.06
    kenin
    0.06
     pathMatch
    0.06
    ?key
    0.06
    Activations Density 0.000%

    No Known Activations