© 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. 39818
    Prev
    Next
    INDEX
    Explanations

    phrases that describe methods or ways of doing something

    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
     eve
    -0.07
     ÑĤака
    -0.07
    itty
    -0.07
    addock
    -0.07
    ewan
    -0.07
    IGHL
    -0.06
    ucle
    -0.06
    inge
    -0.06
    ฺ
    -0.06
    é³´
    -0.06
    POSITIVE LOGITS
    urname
    0.07
    SETTING
    0.07
    emu
    0.07
    /by
    0.07
    etooth
    0.06
    ojis
    0.06
    byn
    0.06
    tml
    0.06
    åħ
    0.06
    elps
    0.06
    Activations Density 0.002%

    No Known Activations