© 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. 28504
    Prev
    Next
    INDEX
    Explanations

    references to code or programming elements

    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
    hythm
    -0.06
    ,
    -0.06
    FD
    -0.06
    (
    -0.06
    igu
    -0.06
    unker
    -0.06
    icolor
    -0.06
     ků
    -0.05
    ikit
    -0.05
    391
    -0.05
    POSITIVE LOGITS
    InSection
    0.08
    reesome
    0.07
    елик
    0.07
    ë¦¬ë¡ľ
    0.07
    -fontawesome
    0.07
    âĶIJ
    0.07
    chein
    0.07
    :č↵č↵
    0.07
    ãĤ¹ãĤ«
    0.07
    ãģĹãģ®
    0.07
    Activations Density 0.000%

    No Known Activations