© 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 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. 29297
    Prev
    Next
    INDEX
    Explanations

    phrases related to relocation and immigration processes

    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
    uchi
    -0.07
    aina
    -0.06
    ury
    -0.06
    326
    -0.06
    its
    -0.06
    ena
    -0.06
     Dodd
    -0.05
    aye
    -0.05
     ÙħعÙĨ
    -0.05
    inda
    -0.05
    POSITIVE LOGITS
    Invoker
    0.08
     immigration
    0.07
     em
    0.07
     immigr
    0.07
     Fres
    0.07
    kommen
    0.07
    chsel
    0.07
    nodoc
    0.06
     account
    0.06
    888
    0.06
    Activations Density 0.001%

    No Known Activations