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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 62102
    Prev
    Next
    INDEX
    Explanations

    occurrences of URLs, specifically those starting with 'http' or 'https'

    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
    Ñĥди
    -0.07
    osta
    -0.07
    estar
    -0.07
    achs
    -0.07
    azu
    -0.06
     pretext
    -0.06
    Äįe
    -0.06
    ildiÄŁi
    -0.06
    ánh
    -0.06
    upp
    -0.06
    POSITIVE LOGITS
    ://
    0.10
     Gord
    0.06
    ìĿ´íĦ°
    0.06
    elerik
    0.06
     URLWithString
    0.06
     UIControl
    0.06
    823
    0.06
    ico
    0.06
    reas
    0.06
    uentes
    0.06
    Activations Density 0.007%

    No Known Activations