© 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. 79245
    Prev
    Next
    INDEX
    Explanations

    instances of migration and relocation related to job opportunities

    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
    OI
    -0.08
    lasses
    -0.07
    (åľŁ
    -0.07
    inston
    -0.07
    ãĥ³ãĤ¬
    -0.07
    oldem
    -0.07
    rana
    -0.07
     retired
    -0.07
    ÃŃda
    -0.07
    æķ·
    -0.06
    POSITIVE LOGITS
     city
    0.11
    -city
    0.10
     cities
    0.09
    Cities
    0.09
    city
    0.09
     City
    0.09
     urban
    0.09
     Cities
    0.08
    .city
    0.08
    åŁİå¸Ĥ
    0.08
    Activations Density 0.109%

    No Known Activations