© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 131064
    Prev
    Next
    INDEX
    Explanations

    key phrases related to funding, eligibility, and improvement efforts in various 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
     totiž
    -0.10
     zwar
    -0.09
    uled
    -0.07
    âijł
    -0.07
    .gwt
    -0.07
    rak
    -0.07
    kart
    -0.07
    obraz
    -0.07
    bourg
    -0.07
    idot
    -0.07
    POSITIVE LOGITS
     thereof
    0.19
     accordingly
    0.14
     deren
    0.11
     them
    0.11
     therein
    0.10
    ãģĿãģĵ
    0.10
     consequently
    0.10
     ìĿ´ë¥¼
    0.10
    ãģĿãĤĮ
    0.10
     it
    0.10
    Activations Density 0.333%

    No Known Activations