© 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. 17-LLAMASCOPE-RES-131K
    11. 2350
    Prev
    Next
    INDEX
    Explanations

    phrases related to email communications and potential consequences of actions in a business context

    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
    emme
    -0.07
    IMA
    -0.07
    ito
    -0.07
    å³°
    -0.07
    меÑĪ
    -0.07
    Ñĩи
    -0.06
    ennon
    -0.06
    ona
    -0.06
     reh
    -0.06
    æĤª
    -0.06
    POSITIVE LOGITS
     death
    0.10
     demise
    0.10
     terminal
    0.09
     fatal
    0.09
     collapse
    0.09
     die
    0.09
     eventually
    0.08
     doom
    0.08
     DIE
    0.08
     soon
    0.08
    Activations Density 0.085%

    No Known Activations