© 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. 89554
    Prev
    Next
    INDEX
    Explanations

    instances of significant gains or losses, particularly in quantitative 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
    eltas
    -0.06
    pars
    -0.06
    508
    -0.06
    باÙĨ
    -0.06
    iciary
    -0.06
     мил
    -0.06
    verages
    -0.06
    ãĥ¼ãĥī
    -0.06
    agency
    -0.06
    agrams
    -0.06
    POSITIVE LOGITS
    宾
    0.07
     conclusion
    0.07
     concluded
    0.06
     sonu
    0.06
     outcomes
    0.06
     overall
    0.06
    odium
    0.06
    quete
    0.06
     increased
    0.06
    alu
    0.06
    Activations Density 0.062%

    No Known Activations