© 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. 170
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and ingredient preparations

    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
    WhiteSpace
    -0.07
    buz
    -0.07
     dán
    -0.07
    иÑĩа
    -0.07
    //{{
    -0.07
    ÃĹ↵↵
    -0.07
    toi
    -0.07
    епÑĤи
    -0.06
     Kuzey
    -0.06
    eldom
    -0.06
    POSITIVE LOGITS
     bre
    0.07
    jie
    0.06
    루
    0.06
    оÑĪ
    0.06
     Dent
    0.06
    eger
    0.06
    eno
    0.05
    uhe
    0.05
    eward
    0.05
     Ba
    0.05
    Activations Density 0.057%

    No Known Activations