© 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. 71725
    Prev
    Next
    INDEX
    Explanations

    significant references to geographical locations or travel destinations

    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
    ÅĻet
    -0.08
    avaÅŁ
    -0.07
    remen
    -0.07
    åľŃ
    -0.07
    arters
    -0.07
    ukan
    -0.06
    illaume
    -0.06
    muÅŁ
    -0.06
     CPR
    -0.06
    دÛĮگر
    -0.06
    POSITIVE LOGITS
    elp
    0.07
     proverb
    0.06
    aver
    0.06
     twig
    0.06
     teaser
    0.06
    ÑīеÑģÑĤво
    0.06
    entine
    0.06
    æ¬ł
    0.06
    Ïīδ
    0.06
     Juliet
    0.06
    Activations Density 0.013%

    No Known Activations