© 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. 84363
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and time-related information

    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
    éĶ¦
    -0.08
    braco
    -0.07
    relude
    -0.07
    AffineTransform
    -0.07
    iken
    -0.07
    ikk
    -0.07
    å£
    -0.06
    ä¿
    -0.06
     ciz
    -0.06
    ierge
    -0.06
    POSITIVE LOGITS
    öh
    0.06
    ↵  ↵
    0.06
    angkan
    0.06
    rray
    0.06
    rary
    0.06
    Ïģά
    0.06
    raman
    0.05
     esa
    0.05
     Blank
    0.05
    azy
    0.05
    Activations Density 0.005%

    No Known Activations