© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28699
    Prev
    Next
    INDEX
    Explanations

    words or phrases with significant emotional weight or impact

    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
    Æ°á»Łng
    -0.07
    teri
    -0.07
    kont
    -0.07
    aben
    -0.07
    ãģĻãģİ
    -0.07
    ãĤ¥
    -0.07
    OKIE
    -0.07
    Äįin
    -0.07
    ceed
    -0.06
     ê
    -0.06
    POSITIVE LOGITS
     WA
    0.07
     Ohio
    0.07
     VA
    0.07
     TX
    0.07
     USA
    0.07
     IL
    0.07
     CA
    0.07
    WA
    0.07
     OH
    0.06
     Illinois
    0.06
    Activations Density 0.068%

    No Known Activations