© 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. 15220
    Prev
    Next
    INDEX
    Explanations

    references to ethical theories and principles

    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
    .neo
    -0.07
    iling
    -0.07
    ampus
    -0.07
     Circus
    -0.07
    asso
    -0.07
    alus
    -0.06
    orr
    -0.06
     лов
    -0.06
    меÑĩ
    -0.06
    pd
    -0.06
    POSITIVE LOGITS
    pedia
    0.07
    rium
    0.07
    bard
    0.06
     elsewhere
    0.06
    JT
    0.06
     @(
    0.06
     JT
    0.06
    .GraphicsUnit
    0.06
     volum
    0.05
     ÑģобÑĭ
    0.05
    Activations Density 0.008%

    No Known Activations