© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 126994
    Prev
    Next
    INDEX
    Explanations

    references to cities and urban environments

    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
    uten
    -0.07
    orton
    -0.07
    /buttons
    -0.07
    alian
    -0.07
    olan
    -0.07
    orny
    -0.07
    utin
    -0.07
    άλι
    -0.07
    PEED
    -0.07
    reation
    -0.07
    POSITIVE LOGITS
    -wide
    0.07
     addCriterion
    0.06
    PB
    0.05
    olf
    0.05
    æŀĿ
    0.05
    ve
    0.05
    oney
    0.05
     itself
    0.05
    ÃŃch
    0.05
     charm
    0.05
    Activations Density 0.016%

    No Known Activations