© 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. 57417
    Prev
    Next
    INDEX
    Explanations

    references to personal information handling and privacy policies

    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
    ucci
    -0.07
    cdf
    -0.06
    enberg
    -0.06
    bring
    -0.06
    435
    -0.06
    inki
    -0.06
    signed
    -0.06
    ắn
    -0.06
    ฯ
    -0.06
    uest
    -0.06
    POSITIVE LOGITS
    col
    0.07
     stored
    0.07
     storage
    0.07
     åħ±
    0.06
    dük
    0.06
    ecut
    0.06
     PUS
    0.06
     private
    0.06
    663
    0.06
    stored
    0.06
    Activations Density 0.003%

    No Known Activations