© 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. 40054
    Prev
    Next
    INDEX
    Explanations

    details about potty training experiences and successes

    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
    amarin
    -0.07
    illez
    -0.07
    dbg
    -0.07
    uffers
    -0.07
    apur
    -0.07
    çĤ®
    -0.07
    illard
    -0.07
    ä¸įè¿ĩ
    -0.07
    usercontent
    -0.07
     stron
    -0.07
    POSITIVE LOGITS
    eya
    0.06
    arus
    0.06
    ãģ¨ãģĨ
    0.06
     independently
    0.06
     grown
    0.05
    anship
    0.05
     Peer
    0.05
    iken
    0.05
     Jr
    0.05
     zoning
    0.05
    Activations Density 0.011%

    No Known Activations