© 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. 15-LLAMASCOPE-RES-131K
    11. 90762
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical or administrative locations

    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
    TestMethod
    -0.06
    aden
    -0.06
     Pur
    -0.05
    ft
    -0.05
     Scho
    -0.05
    ards
    -0.05
    ocene
    -0.05
    abel
    -0.05
    vection
    -0.05
     nurt
    -0.05
    POSITIVE LOGITS
    indow
    0.08
     رض
    0.07
    CAF
    0.07
    à¹Ģà¸Ķà¸Ńร
    0.07
    .mx
    0.07
     ÙģÙĩÙħ
    0.07
    AtPath
    0.07
    raki
    0.06
    ầm
    0.06
    kov
    0.06
    Activations Density 0.000%

    No Known Activations