© 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. 128804
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to form labels and titles

    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
    maal
    -0.08
    eton
    -0.06
    egan
    -0.06
    iasi
    -0.06
     Bud
    -0.06
     обоÑĢ
    -0.06
    ells
    -0.06
    uer
    -0.06
    assic
    -0.06
    exus
    -0.06
    POSITIVE LOGITS
    spacer
    0.07
     hã
    0.06
     Yao
    0.06
    setFlash
    0.06
     QLabel
    0.06
    phe
    0.06
    plor
    0.06
    bolt
    0.06
    á»Ŀi
    0.06
     ...(
    0.06
    Activations Density 0.007%

    No Known Activations