© 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. 129652
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "this" and variations of it in specific contexts

    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
    askell
    -0.07
    iaux
    -0.07
    venta
    -0.07
    iosper
    -0.07
    ahas
    -0.07
     chod
    -0.07
    inati
    -0.07
    ãģ°ãģĭãĤĬ
    -0.06
    anches
    -0.06
    quette
    -0.06
    POSITIVE LOGITS
    ếp
    0.06
    ï¼
    0.06
    oretical
    0.06
     Gentle
    0.06
    Uvs
    0.06
    SED
    0.06
     optional
    0.06
    æĺ¯æĪij
    0.05
     ones
    0.05
    ë³Ģ
    0.05
    Activations Density 0.015%

    No Known Activations