© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95737
    Prev
    Next
    INDEX
    Explanations

    references to the USA Basketball team and its players

    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
    auce
    -0.07
    IXEL
    -0.07
    icks
    -0.07
    otron
    -0.06
    egin
    -0.06
    inel
    -0.06
    haf
    -0.06
    mund
    -0.06
    acific
    -0.06
    ToFit
    -0.06
    POSITIVE LOGITS
    uras
    0.07
    ίδ
    0.06
    	RT
    0.06
    -host
    0.06
     prest
    0.06
    ounded
    0.06
     Há»ĵ
    0.06
    bound
    0.06
    \common
    0.05
    üc
    0.05
    Activations Density 0.005%

    No Known Activations