© 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. 58822
    Prev
    Next
    INDEX
    Explanations

    references to unique cities and their characteristics

    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
    ppard
    -0.07
    AreaView
    -0.06
    rish
    -0.06
    icht
    -0.06
    arer
    -0.06
    tesy
    -0.06
    .psi
    -0.06
    .setDefault
    -0.06
    =find
    -0.06
    .CodeAnalysis
    -0.06
    POSITIVE LOGITS
     city
    0.10
     its
    0.09
     itself
    0.09
    -city
    0.09
    city
    0.08
    adol
    0.08
     City
    0.07
    .city
    0.07
    orm
    0.07
     tourism
    0.07
    Activations Density 0.064%

    No Known Activations