© 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. 57150
    Prev
    Next
    INDEX
    Explanations

    occurrences of website URLs, particularly related to JavaScript libraries and CSS frameworks

    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
    odore
    -0.07
    owan
    -0.07
    rack
    -0.07
    ijk
    -0.07
    wner
    -0.07
    urum
    -0.07
    ifu
    -0.07
    formik
    -0.06
    åĮ
    -0.06
    anax
    -0.06
    POSITIVE LOGITS
    atte
    0.07
     Maul
    0.06
     Google
    0.06
    atos
    0.06
     Meg
    0.06
    357
    0.06
     pub
    0.06
    ilion
    0.06
    ato
    0.06
    ÙĬÙĦا
    0.06
    Activations Density 0.002%

    No Known Activations