© 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. 89139
    Prev
    Next
    INDEX
    Explanations

    references to additional information or details

    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
     Thá»ĭ
    -0.06
    102
    -0.06
     eventual
    -0.06
    101
    -0.06
     vs
    -0.06
    udeau
    -0.06
     share
    -0.06
    adden
    -0.06
    ahrungen
    -0.05
    ÃŃch
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĥī
    0.07
    .scalablytyped
    0.07
    ëĮĢë¡ľ
    0.07
    ãĥ³ãĥĨ
    0.07
    اراÙĨ
    0.07
     بداÙĨ
    0.07
    ê°ľìĿĺ
    0.07
     createState
    0.07
    -height
    0.07
     Prem
    0.07
    Activations Density 0.016%

    No Known Activations