© 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. 98336
    Prev
    Next
    INDEX
    Explanations

    phrases involving the concept of choices or options

    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
    ÑĢÑı
    -0.08
     ByVal
    -0.07
    akk
    -0.07
    ç
    -0.07
    ilogy
    -0.06
    tsky
    -0.06
    adratic
    -0.06
    .addObserver
    -0.06
    interop
    -0.06
     NSLocalizedString
    -0.06
    POSITIVE LOGITS
     opportunity
    0.09
     opportunities
    0.07
     chance
    0.07
     option
    0.07
     pressing
    0.06
    æ½
    0.06
     Möglich
    0.06
    pressed
    0.06
     options
    0.06
     choice
    0.06
    Activations Density 0.043%

    No Known Activations