© 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. 88349
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure related to documents and forms

    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
    /name
    -0.06
    >Title
    -0.06
    Æ°á»Ŀng
    -0.06
    aporan
    -0.06
    ÃŃc
    -0.06
     Border
    -0.06
    _name
    -0.06
    ALAR
    -0.06
    æŀ¶
    -0.06
     jag
    -0.06
    POSITIVE LOGITS
     explan
    0.09
     Lorem
    0.08
     explanation
    0.07
     descr
    0.07
     description
    0.07
     erm
    0.07
    説æĺİ
    0.07
     explain
    0.07
     explained
    0.06
    ctica
    0.06
    Activations Density 0.039%

    No Known Activations