© 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. 125819
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Brookhaven."

    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
    STA
    -0.07
    èŃ
    -0.06
     broadly
    -0.06
     Fres
    -0.06
     Hier
    -0.06
    oman
    -0.06
    ija
    -0.06
     Robbins
    -0.06
    VID
    -0.06
    IES
    -0.06
    POSITIVE LOGITS
    usch
    0.08
    hani
    0.07
    ushima
    0.07
    ÑĴ
    0.07
    iding
    0.07
    .Guna
    0.07
     Enemies
    0.06
    nings
    0.06
    麻
    0.06
    ibil
    0.06
    Activations Density 0.000%

    No Known Activations