© 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. 15-LLAMASCOPE-RES-131K
    11. 27362
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface (UI) manipulation in code

    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
     desar
    -0.07
    αι
    -0.07
    ught
    -0.07
    obuf
    -0.07
    wang
    -0.06
    anten
    -0.06
    çħ§
    -0.06
    ราย
    -0.06
    ustr
    -0.06
    Thunk
    -0.06
    POSITIVE LOGITS
    gren
    0.08
    dia
    0.07
    LOBAL
    0.06
    iani
    0.06
     Chambers
    0.06
    istrovstvÃŃ
    0.06
     ÐŁÑĢа
    0.06
     anzeigen
    0.06
     Hitch
    0.06
    feld
    0.06
    Activations Density 0.001%

    No Known Activations