© 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. 127914
    Prev
    Next
    INDEX
    Explanations

    attributes and properties related to user interface states in web development

    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
    ugo
    -0.07
    üçük
    -0.07
    azo
    -0.07
    enti
    -0.07
    radient
    -0.07
     neod
    -0.06
    neo
    -0.06
    allas
    -0.06
    ÑĢиÑģÑĤи
    -0.06
    umo
    -0.06
    POSITIVE LOGITS
     revel
    0.06
    ëĭ¹
    0.06
    osate
    0.06
    ered
    0.06
     lick
    0.06
    licken
    0.06
    ENER
    0.06
    =true
    0.06
     Scal
    0.06
    ness
    0.06
    Activations Density 0.010%

    No Known Activations