© 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. 98303
    Prev
    Next
    INDEX
    Explanations

    contractions indicating possession or relationships

    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
     VÅ¡ech
    -0.08
    pper
    -0.07
    oho
    -0.06
    åĬ¨çĶŁæĪIJ
    -0.06
    ÅŁt
    -0.06
    ä¿Ĭ
    -0.06
    etc
    -0.06
    ple
    -0.06
    жд
    -0.06
    wers
    -0.06
    POSITIVE LOGITS
    .mx
    0.06
    mary
    0.06
     why
    0.06
    ÏĢη
    0.06
     how
    0.06
     opportunity
    0.06
    arie
    0.06
    "<?
    0.06
    esium
    0.06
    :::::::
    0.06
    Activations Density 0.011%

    No Known Activations