© 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. 17-LLAMASCOPE-RES-131K
    11. 128313
    Prev
    Next
    INDEX
    Explanations

    geographic locations, particularly neighborhoods or areas in New York City

    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
     ><?
    -0.07
     Salah
    -0.07
    .nasa
    -0.06
    æijĺè¦ģ
    -0.06
     YaÅŁ
    -0.06
     skiing
    -0.06
    ();?>
    -0.06
     å»
    -0.06
     içerisinde
    -0.06
     Genç
    -0.06
    POSITIVE LOGITS
    kee
    0.07
     Jersey
    0.06
     vintage
    0.06
     Vintage
    0.06
    acic
    0.06
    ãĥ³ãĥģ
    0.06
    ?url
    0.06
     Brooklyn
    0.06
     Atlantic
    0.06
     tune
    0.06
    Activations Density 0.000%

    No Known Activations