© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126735
    Prev
    Next
    INDEX
    Explanations

    phrases related to web browser functionality and JavaScript support

    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
    ácil
    -0.07
     revers
    -0.07
    utex
    -0.07
    ยา
    -0.07
    gross
    -0.07
    ipsis
    -0.07
    .Orientation
    -0.06
    Äĥn
    -0.06
    nee
    -0.06
    á»Ŀ
    -0.06
    POSITIVE LOGITS
     modern
    0.08
     Upgrade
    0.06
    modern
    0.06
    ICA
    0.06
    ÏĦοκ
    0.06
    çݰ代
    0.06
     Modern
    0.06
    Modern
    0.06
    hes
    0.06
     Unsupported
    0.06
    Activations Density 0.001%

    No Known Activations