© 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. 93782
    Prev
    Next
    INDEX
    Explanations

    information related to automobile exhibitions and charitable fundraising events

    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
    -0.07
    âĢ¦↵
    -0.06
    
    -0.06
    pare
    -0.05
     Marriott
    -0.05
    reno
    -0.05
    â
    -0.05
     Kov
    -0.05
    âĢ¦
    -0.05
     +
    -0.05
    POSITIVE LOGITS
    defgroup
    0.09
    addtogroup
    0.09
    }elseif
    0.08
     nackte
    0.08
     minh
    0.08
     Demir
    0.08
    è¥
    0.08
    POCH
    0.08
    ADE
    0.08
    ÙħÛĮÙĨ
    0.07
    Activations Density 0.005%

    No Known Activations