© 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. 73448
    Prev
    Next
    INDEX
    Explanations

    references to immigration policies and their implications

    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
    à¹īà¸Ńย
    -0.07
    antino
    -0.07
    iazza
    -0.07
    Uvs
    -0.07
    Ñĥнк
    -0.07
    ynchronously
    -0.07
    uby
    -0.06
    lei
    -0.06
    živ
    -0.06
     Ñģамов
    -0.06
    POSITIVE LOGITS
     labor
    0.11
     labour
    0.10
     Labour
    0.09
     Labor
    0.09
    åĬ³
    0.08
    Labour
    0.07
     wages
    0.06
     demand
    0.06
     fill
    0.06
     Fill
    0.06
    Activations Density 0.004%

    No Known Activations