© 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. 81804
    Prev
    Next
    INDEX
    Explanations

    prominent names of celebrities and notable figures

    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
    :UIAlert
    -0.07
    -être
    -0.07
    oji
    -0.06
    )const
    -0.06
    fort
    -0.06
     forControlEvents
    -0.06
     geil
    -0.06
    .opendaylight
    -0.06
     addCriterion
    -0.06
     opat
    -0.06
    POSITIVE LOGITS
    ा:
    0.08
    nova
    0.07
    _-_
    0.07
     تصÙħ
    0.07
    ãģĹãģ®
    0.07
    ustil
    0.06
    ÑĢив
    0.06
     Kostenlose
    0.06
    Æ°á»Ŀng
    0.06
    arım
    0.06
    Activations Density 0.078%

    No Known Activations