© 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. 97482
    Prev
    Next
    INDEX
    Explanations

    references to significant figures and events related to the Roman Empire

    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
    SharedPointer
    -0.08
     autonom
    -0.07
    Accessory
    -0.07
    ertz
    -0.07
    arta
    -0.07
    ietf
    -0.07
    tplib
    -0.06
    lef
    -0.06
    InnerText
    -0.06
     Leban
    -0.06
    POSITIVE LOGITS
    ge
    0.07
     official
    0.06
     åģ
    0.06
    addle
    0.06
     Roger
    0.06
    ëŁī
    0.05
    bow
    0.05
    ÑĢовиÑĩ
    0.05
    stable
    0.05
     Homo
    0.05
    Activations Density 0.005%

    No Known Activations