© 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. 128844
    Prev
    Next
    INDEX
    Explanations

    statistics and information about water scarcity and access issues

    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
    pill
    -0.08
    illez
    -0.08
    sterol
    -0.08
    iversite
    -0.08
    appers
    -0.07
     Incontri
    -0.07
    icana
    -0.07
    opez
    -0.07
    entiful
    -0.07
    apon
    -0.07
    POSITIVE LOGITS
     rural
    0.07
     Rural
    0.07
     poverty
    0.06
     ar
    0.06
     Mac
    0.06
     retro
    0.06
     conc
    0.06
     ÑĤÑĢа
    0.06
     mag
    0.06
     lack
    0.06
    Activations Density 0.039%

    No Known Activations