© 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. 17-LLAMASCOPE-RES-131K
    11. 129485
    Prev
    Next
    INDEX
    Explanations

    mentions of relationships and family members

    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
    unga
    -0.07
     Trident
    -0.06
    nun
    -0.06
    ello
    -0.06
    aben
    -0.06
    Rich
    -0.06
    NgModule
    -0.06
     Mess
    -0.06
    uyu
    -0.05
    nty
    -0.05
    POSITIVE LOGITS
    phia
    0.08
     vợ
    0.08
    icket
    0.07
    ÑģпÑĸлÑĮ
    0.07
    *=*=
    0.07
    Ä°Åŀ
    0.07
     cuckold
    0.07
    ISIBLE
    0.07
    IDEO
    0.06
     marital
    0.06
    Activations Density 0.061%

    No Known Activations