© 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. 9-LLAMASCOPE-RES-131K
    11. 95182
    Prev
    Next
    INDEX
    Explanations

    instances of proper nouns and place names

    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
    horn
    -0.06
    gh
    -0.06
     bog
    -0.05
    omore
    -0.05
    lij
    -0.05
    ific
    -0.05
    iny
    -0.05
    lien
    -0.05
     travers
    -0.05
    phasis
    -0.05
    POSITIVE LOGITS
    endon
    0.08
     Ùħرات
    0.07
    ÑĤÑİ
    0.07
    кÑĥлÑı
    0.07
     FactoryBot
    0.07
    'icon
    0.07
     ^{°}
    0.07
    ardy
    0.07
    ondo
    0.07
    å¿į
    0.07
    Activations Density 0.013%

    No Known Activations