© 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. 75798
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistics related to births and population data

    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
    eyn
    -0.07
    _CY
    -0.07
    ży
    -0.06
    ей
    -0.06
    oogle
    -0.06
    ao
    -0.06
    dn
    -0.06
    áce
    -0.06
    eward
    -0.06
    der
    -0.06
    POSITIVE LOGITS
     wom
    0.07
     Exchange
    0.06
    .Large
    0.06
    oment
    0.06
    ilden
    0.06
    æĭ¬
    0.06
    Lib
    0.06
    Exchange
    0.06
    ONT
    0.06
     St
    0.06
    Activations Density 0.050%

    No Known Activations